Humanity&#x27;s Last Exam

claude-opus-5

Anthropic

closed

Score input

64.7%

claude-mythos-5

Anthropic

closed

Source carrier

64.5%

muse-spark-1-1

Meta

closed

Score input

62.1%

gpt-5.4

OpenAI

closed

Source carrier

58.7%

claude-opus-4-8

Anthropic

closed

Source carrier

57.9%

claude-sonnet-5

Anthropic

closed

Source carrier

57.4%

gpt-5.5

OpenAI

closed

Source carrier

57.2%

kimi-k3

Moonshot AI

open

Score input

56%

claude-fable-5

Anthropic

closed

Score input

55.5%

#10

GLM-5.3-Flash

glm-5.3-flash

Z.AI

open

Public reference

55.3%

#11

claude-opus-4-7

Anthropic

closed

Source carrier

54.7%

#12

glm-5-2

Z.AI

open

Source carrier

54.7%

#13

hy3

Tencent

open

Score input

53.2%

#14

claude-opus-4-6

Anthropic

closed

Source carrier

53%

#15

glm-5-1

Z.AI

open

Source carrier

52.3%

#16

glm-5

Z.AI

open

Source carrier

50.4%

#17

muse-spark

Meta

closed

Source carrier

50.4%

#18

gpt-5.6-sol

OpenAI

closed

Score input

49.5%

#19

claude-sonnet-4-6

Anthropic

closed

Source carrier

49%

#20

mimo-v2-5-pro

Xiaomi

open

Source carrier

48%

#21

Inkling-Small

thinkingmachines/inkling-small

Thinking Machines Lab

open

Source carrier

47.8%

#22

agents-a1

InternScience

open

Source carrier

47.6%

#23

inkling

Thinking Machines Lab

open

Source carrier

46%

#24

Muse Spark 1.2

muse-spark-1-2

Meta

announced-open

Score input

45.5%

#25

Gemini 3.1 Pro Preview

gemini-3.1-pro-preview

Google

closed

Public reference

44.7%

#26

Qwen3.8 Max

qwen3.8-max

Alibaba Cloud

open

Score input

43.6%

#27

gpt-5.6-terra

OpenAI

closed

Score input

42.9%

#28

Grok 4.6

grok-4.6

xAI

closed

Score input

42.9%

#29

grok-4.5

xAI

closed

Score input

42.7%

#30

GLM-5.3

glm-5.3

Z.AI

announced-open

Score input

42.3%

#31

gpt-5.4-mini

OpenAI

closed

Source carrier

41.5%

#32

qwen3.7-max

Alibaba Cloud

closed

Source carrier

41.4%

#33

DeepSeek V4 Pro 0813

DeepSeek-V4-Pro-0813

DeepSeek

open

Public reference

41.0%

#34

gemini-3.6-flash

Google

closed

Score input

40.8%

#35

gemini-3.5-flash

Google

closed

Score input

40.2%

#36

gpt-5.3-codex

OpenAI

closed

Public reference

39.9%

#37

gpt-5.6-luna

OpenAI

closed

Score input

39.5%

#38

Gemini 3.7 Flash

gemini-3.7-flash

Google

closed

Score input

39.0%

#39

Qwen3.8-Flash-Next

Qwen/Qwen3.8-Flash-Next

Alibaba Cloud

open

Public reference

38.0%

#40

deepseek-v4-pro

DeepSeek

open

Source carrier

37.7%

#41

gpt-5.4-nano

OpenAI

closed

Source carrier

37.7%

#42

MiniMax-M3

MiniMax

open

Public reference

37.1%

#43

kimi-k2.6

Moonshot AI

open

Public reference

35.9%

#44

gpt-5.2

OpenAI

closed

Public reference

35.4%

#45

grok-4.3

xAI

closed

Public reference

35.0%

#46

deepseek-v4-flash

DeepSeek

open

Source carrier

34.8%

#47

DeepSeek V4 Flash Vision Exp

qwen3.7-plus

Alibaba Cloud

closed

Source carrier

34.7%

#48

deepseek-v4-flash-vision-exp

DeepSeek

—

Public reference

34.5%

#49

LongCat-2.0

meituan-longcat/LongCat-2.0

Meituan

open

Score input

33.7%

#50

gpt-5.2-codex

OpenAI

closed

Source carrier

33.5%

#51

kimi-k2.7-code

Moonshot AI

open

Source carrier

32.8%

#52

Grok 4.20

grok-4.20

xAI

closed

Public reference

32.2%

#53

claude-opus-4-5

Anthropic

closed

Source carrier

30.8%

#54

Qwen3.8-27B

Qwen/Qwen3.8-27B

Alibaba Cloud

open

Score input

30.8%

#55

kimi-k2.5

Moonshot AI

open

Score input

30.7%

#56

Qwen/Qwen3.5-397B-A17B

Alibaba Cloud

open

Score input

29.0%

#57

qwen3-6-max-preview

Alibaba Cloud

closed

Source carrier

28.9%

#58

Qwen3.6 Max

qwen3.6-max

Alibaba Cloud

closed

Public reference

28.9%

#59

qwen3-6-plus

Alibaba Cloud

closed

Source carrier

28.8%

#60

Solar Open 2 250B

upstage/Solar-Open2-250B

Upstage

open

Score input

28.8%

#61

claude-opus-4-5-thinking

Anthropic

closed

Source carrier

28.4%

#62

mimo-v2-pro

Xiaomi

closed

Source carrier

28.3%

#63

minimax-m2-7

MiniMax

open

Source carrier

28.1%

#64

nemotron-3-ultra-550b

NVIDIA

open

Source carrier

26.7%

#65

gpt-5

OpenAI

closed

Public reference

26.5%

#66

gemma-4-31b

Google

open

Source carrier

26.5%

#67

gpt-5.1

OpenAI

closed

Source carrier

26.5%

#68

qwen3-max

Alibaba Cloud

closed

Public reference

26.2%

#69

GPT-5 Codex

gpt-5-codex

OpenAI

closed

Public reference

25.6%

#70

hy3-preview

Tencent

open

Source carrier

25.5%

#71

glm-5-turbo

Z.AI

closed

Source carrier

25.4%

#72

Qwen/Qwen3.5-122B-A10B

Alibaba Cloud

open

Score input

25.2%

#73

MiMo-V2.5

mimo-v2.5

Xiaomi

open

Public reference

25.2%

#74

glm-4.7

Z.AI

open

Public reference

25.1%

#75

qwen3.6-27b

Alibaba Cloud

open

Source carrier

24%

#76

grok-4

xAI

closed

Public reference

23.9%

#77

Qwen3.5 122B

qwen3.5-122b-a10b

Alibaba Cloud

open

Score input

23.4%

#78

gpt-5-1-codex

OpenAI

closed

Source carrier

23.4%

#79

gpt-5-1-codex-max

OpenAI

closed

Source carrier

23.4%

#80

Kimi K2 Thinking

kimi-k2-thinking

Moonshot AI

open

Public reference

22.3%

#81

Qwen/Qwen3.6-35B-A3B

Alibaba Cloud

open

Score input

22.2%

#82

deepseek-v3.2

DeepSeek

open

Public reference

22.2%

#83

qwen3.5-27b

Alibaba Cloud

open

Source carrier

22.2%

#84

MiniMax M2.1

minimax-m2.1

MiniMax

open

Public reference

22.2%

#85

Muse Glimmer 30B

meta-models/Muse-Glimmer-30B

Meta

open

Score input

22%

#86

gemini-2.5-pro

Google

closed

Public reference

21.1%

#87

OpenAI

closed

Public reference

20.0%

#88

mimo-v2-omni

Xiaomi

closed

Source carrier

19.9%

#89

step-3-7-flash

StepFun

open

Source carrier

19.9%

#90

Qwen3.5 35B

qwen3.5-35b-a3b

Alibaba Cloud

open

Score input

19.7%

#91

qwen3-5-35b-a3b

Alibaba Cloud

open

Source carrier

19.7%

#92

google/gemma-4-26b-a4b-it

Google

open

Score input

19.3%

#93

Nemotron 3 Super

nemotron-3-super-120b

NVIDIA

open

Score input

19.2%

#94

MiniMax M2.5

minimax-m2.5

MiniMax

open

Public reference

19.1%

#95

gpt-oss-120b

OpenAI

open

Source carrier

18.5%

#96

Gemma 4 26B

gemma-4-26b-a4b

Google

open

Score input

18.3%

#97

grok-4-1-fast-reasoning

xAI

closed

Source carrier

17.6%

#98

o4-mini

OpenAI

closed

Public reference

17.5%

#99

gemini-3.5-flash-lite

Google

closed

Public reference

17.5%

#100

Claude Sonnet 4.5

claude-sonnet-4-5

Anthropic

closed

Score input

17.3%

#101

grok-4-fast-reasoning

xAI

closed

Source carrier

17%

#102

Grok 4 Fast

grok-4-fast

xAI

closed

Public reference

17.0%

#103

gemini-3.1-flash-lite

Google

closed

Source carrier

16.2%

#104

trinity-large-thinking

Arcee AI

open

Score input

15.8%

#105

glm-5v-turbo

Z.AI

closed

Source carrier

15.8%

#106

DeepSeek V3.1 Terminus

deepseek-v3.1-terminus

DeepSeek

open

Public reference

15.2%

#107

deepseek-r1

DeepSeek

open

Source carrier

14.9%

#108

google/gemma-4-12B

Google

open

Source carrier

14.8%

#109

trinity-large-preview

Arcee AI

open

Source carrier

14.7%

#110

GPT-5 mini

gpt-5-mini

OpenAI

closed

Public reference

14.6%

#111

deepseek-v3-1

DeepSeek

open

Public reference

14.3%

#112

gemini-3-flash

Google

closed

Source carrier

14.1%

#113

Qwen3.5 Omni Plus

qwen3.5-omni-plus

Alibaba Cloud

closed

Public reference

13.9%

#114

mistralai/Mistral-Medium-3.5-128B

Mistral AI

open

Score input

13.8%

#115

glm-4.6

Z.AI

open

Public reference

13.3%

#116

k-exaone

LG AI Research

closed

Source carrier

13.1%

#117

Mistral Medium 3.5

mistral-medium-3-5

Mistral AI

open

Public reference

12.8%

#118

gemini-2.5-flash

Google

closed

Public reference

12.7%

#119

MiniMax M2

minimax-m2

MiniMax

open

Public reference

12.5%

#120

claude-4-1-opus-thinking

Anthropic

closed

Source carrier

11.9%

#121

Claude Opus 4.1

claude-opus-4-1

Anthropic

closed

Score input

11.9%

#122

Claude Opus 4

claude-opus-4

Anthropic

closed

Score input

11.7%

#123

command-a-plus

Cohere

open

Source carrier

11.4%

#124

nemotron-3-nano-30b

NVIDIA

open

Score input

11.4%

#125

Grok 3 mini

grok-3-mini

xAI

closed

Score input

11.1%

#126

Claude Sonnet 3.7

claude-3-7-sonnet

Anthropic

closed

Score input

10.3%

#127

sarvam-105b

Sarvam

open

Source carrier

10.1%

#128

mistral-small-2603

Mistral AI

open

Score input

9.9%

#129

gpt-oss-20b

OpenAI

open

Source carrier

9.8%

#130

Claude Sonnet 4

claude-sonnet-4

Anthropic

closed

Score input

9.6%

#131

Nova 2 Pro

nova-2-pro-preview

Amazon

closed

Score input

8.9%

#132

OpenAI

closed

Source carrier

8.7%

#133

Ling 2.6 1T

ling-2.6-1t

InclusionAI

open

Public reference

8.2%

#134

nemotron-ultra-253b

NVIDIA

open

Source carrier

8.1%

#135

OpenAI

closed

Public reference

7.7%

#136

grok-code-fast-1

xAI

closed

Source carrier

7.5%

#137

kimi-k2

Moonshot AI

closed

Source carrier

#138

sarvam-30b

Sarvam

open

Source carrier

#139

lfm2-5-8b-a1b

LiquidAI

open

Source carrier

6.9%

#140

glm-4-5-air

Z.AI

closed

Source carrier

6.8%

#141

granite-4-0-h-350m

IBM

open

Source carrier

6.4%

#142

Kimi K2 0905

kimi-k2-0905

Moonshot AI

open

Public reference

6.3%

#143

ling-2-6-flash

InclusionAI

open

Source carrier

6.2%

#144

exaone-4-0-1-2b

LG AI Research

open

Source carrier

5.8%

#145

granite-4-0-350m

IBM

open

Source carrier

5.7%

#146

deepseek-r1-distill-qwen-32b

DeepSeek

open

Source carrier

5.5%

#147

nemotron-3-nano-omni-30b-a3b

NVIDIA

open

Source carrier

5.3%

#148

granite-4-0-1b

IBM

open

Source carrier

5.1%

#149

lfm2-5-vl-1-6b-extract

LiquidAI

open

Source carrier

5.1%

#150

gpt-4-1-mini

OpenAI

closed

Score input

5.0%

#151

granite-4-0-h-1b

IBM

open

Source carrier

#152

grok-4-1-fast

xAI

closed

Source carrier

#153

llama-4-maverick

Meta

open

Score input

4.9%

#154

exaone-4-0-32b

LG AI Research

open

Source carrier

4.9%

#155

gemini-1-5-pro

Google

closed

Source carrier

4.9%

#156

gemma-4-e2b

Google

open

Source carrier

4.8%

#157

gemma-3-27b

Google

open

Source carrier

4.7%

#158

gemini-1-0-pro

Google

closed

Source carrier

4.6%

#159

gpt-4-1

OpenAI

closed

Source carrier

4.6%

#160

llama-4-scout

Meta

open

Source carrier

4.3%

#161

mistral-medium-3

Mistral AI

closed

Source carrier

4.3%

#162

Claude Haiku 4.5

claude-haiku-4-5-20251001

Anthropic

closed

Score input

4.3%

#163

llama-3-1-405b

Meta

open

Source carrier

4.2%

#164

mistral-large-2512

Mistral AI

open

Source carrier

4.1%

#165

phi-4

Microsoft

open

Source carrier

4.1%

#166

claude-4-sonnet

Anthropic

closed

Source carrier

#167

gpt-4o-mini

OpenAI

closed

Source carrier

#168

mistral-large-2

Mistral AI

closed

Source carrier

#169

claude-3-haiku

Anthropic

closed

Source carrier

3.9%

#170

gpt-4-1-nano

OpenAI

closed

Source carrier

3.9%

#171

qwen2-5-coder-32b-instruct

Alibaba Cloud

open

Source carrier

3.8%

#172

solar-pro-2

Upstage

closed

Source carrier

3.8%

#173

gemma-4-e4b

Google

open

Source carrier

3.7%

#174

deepseek-v3

DeepSeek

open

Source carrier

3.6%

#175

nova-pro

Amazon

closed

Source carrier

3.4%

#176

gpt-4-turbo

OpenAI

closed

Source carrier

3.3%

#177

gpt-4o

OpenAI

closed

Source carrier

3.3%

#178

claude-3-opus

Anthropic

closed

Source carrier

3.1%

Every distinct dated source-published row for Humanity's Last Exam, including exact model configuration labels
Exact published model / configuration	Canonical product	Score	Version / system	Evidence	Source / observed
Claude Opus 4.7 (Adaptive Reasoning, Max Effort) (Artificial Analysis independent run) claude-opus-4-7-max	Claude Opus 4.7	42.3%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	Claude Opus 4.7 (Adaptive Reasoning, Max Effort) individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29
GLM-5.2 (max) (Artificial Analysis independent run) glm-5-2-max	GLM-5.2	41.1%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	GLM-5.2 (max) individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29
Claude Opus 4.6 (Adaptive Reasoning, Max Effort) (Artificial Analysis independent run) claude-opus-4-6-max	Claude Opus 4.6	39.9%	text-only currentArtificial Analysis text-only HLE evaluation	Public reference · not scored independently-verified	Claude Opus 4.6 (Adaptive Reasoning, Max Effort) individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29
Qwen3.8-Flash-Next (Artificial Analysis independent run) qwen-3-8-flash-next-aa-unspecified	Qwen3.8-Flash-Next	38.0%	text-only currentArtificial Analysis text-only HLE evaluation	Public reference · not scored independently-verified	Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29
LongCat 2.0 (Artificial Analysis independent run) longcat-2-0-default	LongCat-2.0	33.7%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	LongCat 2.0 individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29
Kimi K2.5 (Reasoning) (Artificial Analysis completed independent run) kimi-k2-5-thinking	Kimi K2.5	30.7%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	Kimi K2.5 (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29
Qwen3.5 397B A17B (Reasoning) (Artificial Analysis completed independent run) qwen3-5-397b-thinking	Qwen3.5 397B A17B	29.0%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	Qwen3.5 397B A17B (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29
Qwen3.5 122B A10B (Reasoning) (Artificial Analysis completed independent run) qwen3-5-122b-a10b-aa-reasoning-default	Qwen3.5-122B-A10B	25.2%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	Qwen3.5 122B A10B (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29
Qwen3.6 35B A3B (Reasoning) (Artificial Analysis completed independent run) qwen3-6-35b-a3b-aa-reasoning-default	Qwen3.6-35B-A3B	22.2%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	Qwen3.6 35B A3B (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29
Gemma 4 26B A4B (Reasoning) (Artificial Analysis completed independent run) gemma-4-26b-a4b-aa-reasoning-default	Gemma 4 26B A4B	19.3%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	Gemma 4 26B A4B (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29
Trinity Large Thinking (Artificial Analysis completed independent run) trinity-large-thinking-aa-reasoning-default	Trinity-Large-Thinking	15.8%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	Trinity Large Thinking current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29
DeepSeek V3.1 (Reasoning) (Artificial Analysis independent run) deepseek-v3-1-reasoning-default	DeepSeek V3.1	14.3%	text-only currentArtificial Analysis text-only HLE evaluation	Public reference · not scored independently-verified	DeepSeek V3.1 (Reasoning) individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29
Mistral Medium 3.5 (Artificial Analysis completed independent run) mistral-medium-3-5-128b-aa-reasoning-default	Mistral Medium 3.5 128B	13.8%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	Mistral Medium 3.5 current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) (Artificial Analysis completed independent run) nemotron-3-nano-30b-aa-reasoning-default	Nemotron 3 Nano 30B	11.4%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29
Mistral Small 4 (Reasoning) (Artificial Analysis completed independent run) mistral-small-4-reasoning	Mistral Small 4	9.9%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	Mistral Small 4 (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29
DeepSeek V3.1 (Non-reasoning) (Artificial Analysis independent run) deepseek-v3-1-non-reasoning	DeepSeek V3.1	6.7%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	DeepSeek V3.1 (Non-reasoning) individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29
GPT-4.1 mini (Artificial Analysis completed independent run) gpt-4-1-mini-epoch-gpt-4-1-mini-2025-04-14	GPT-4.1 mini	5.0%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	GPT-4.1 mini current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29
Llama 4 Maverick (Artificial Analysis completed independent run) llama-4-maverick-aa-non-reasoning-default	Llama 4 Maverick	4.9%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	Llama 4 Maverick current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29
Gemma 3 27B Instruct (Artificial Analysis completed independent run) gemma-3-27b-aa-non-reasoning-default	Gemma 3 27B	4.4%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	Gemma 3 27B Instruct current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29
Llama 4 Scout (Artificial Analysis completed independent run) llama-4-scout-aa-non-reasoning-default	Llama 4 Scout	3.8%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	Llama 4 Scout current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29
GPT-4.1 nano (Artificial Analysis completed independent run) gpt-4-1-nano-epoch-gpt-4-1-nano-2025-04-14	GPT-4.1 nano	3.8%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	GPT-4.1 nano current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29
Claude Fable 5 (max; Artificial Analysis independent run) claude-fable-5-max	Claude Fable 5	55.5%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	Claude Fable 5 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
Claude Opus 5 (max; Artificial Analysis independent run) claude-opus-5-max	Claude Opus 5	54.9%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	Claude Opus 5 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
GPT-5.6 Sol (max; Artificial Analysis independent run) gpt-5-6-sol-max	GPT-5.6 Sol	49.5%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	GPT-5.6 Sol individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
Claude Opus 4.8 (max; Artificial Analysis independent run) claude-opus-4-8-max	Claude Opus 4.8	48.7%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	Claude Opus 4.8 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
Kimi K3 (max; Artificial Analysis independent run) kimi-k3-max	Kimi K3	46.9%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	Kimi K3 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
Muse Spark 1.1 (xhigh; Artificial Analysis independent run) muse-spark-1-1-xhigh	Muse Spark 1.1	46.2%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	Muse Spark 1.1 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
GPT-5.5 (xhigh; Artificial Analysis independent run) gpt-5-5-xhigh	GPT-5.5	45.8%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	GPT-5.5 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
Muse Spark 1.2 (xhigh; Artificial Analysis independent run) muse-spark-1-2-xhigh	Muse Spark 1.2	45.5%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	Muse Spark 1.2 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
GPT-5.4 (xhigh; Artificial Analysis independent run) gpt-5-4-xhigh	GPT-5.4	43.7%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	GPT-5.4 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
GPT-5.6 Terra (max; Artificial Analysis independent run) gpt-5-6-terra-max	GPT-5.6 Terra	42.9%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	GPT-5.6 Terra individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
Grok 4.6 (high; Artificial Analysis independent run) grok-4-6-high	Grok 4.6	42.9%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	Grok 4.6 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
Grok 4.5 (high; Artificial Analysis independent run) grok-4-5-aa-2-high	Grok 4.5	42.7%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	Grok 4.5 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
GLM-5.3 (max; Artificial Analysis independent run) glm-5-3-max	GLM-5.3	42.3%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	GLM-5.3 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
Claude Sonnet 5 (max; Artificial Analysis independent run) claude-sonnet-5-max	Claude Sonnet 5	41.3%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	Claude Sonnet 5 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
DeepSeek V4 Pro 0813 (max; Artificial Analysis independent run) deepseek-v4-pro-0813-max	DeepSeek V4 Pro 0813	41.0%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Public reference · not scored independently-verified	DeepSeek V4 Pro 0813 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
Gemini 3.6 Flash (high; Artificial Analysis independent run) gemini-3-6-flash-high	Gemini 3.6 Flash	40.8%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	Gemini 3.6 Flash individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
GLM-5.3-Flash (max; Artificial Analysis independent run) glm-5-3-flash-max	GLM-5.3-Flash	39.9%	text-only currentArtificial Analysis text-only HLE evaluation	Score input independently-verified	GLM-5.3-Flash individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
GPT-5.6 Luna (max; Artificial Analysis independent run) gpt-5-6-luna-max	GPT-5.6 Luna	39.5%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	GPT-5.6 Luna individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
Gemini 3.7 Flash (medium; Artificial Analysis independent run) gemini-3-7-flash-medium	Gemini 3.7 Flash	39.0%	text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation	Score input independently-verified	Gemini 3.7 Flash individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
DeepSeek V4 Flash Vision Exp (max; Artificial Analysis independent run) deepseek-v4-flash-vision-exp-max-harness	DeepSeek V4 Flash Vision Exp	34.5%	text-only currentArtificial Analysis text-only HLE evaluation	Public reference · not scored independently-verified	DeepSeek V4 Flash Vision Exp individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27
GLM-5.3-Flash (max effort, documented default) glm-5-3-flash-max	GLM-5.3-Flash	55.3%	rollingsystem:glm-5-3-flash-launch:hle-tools:0	Public reference · not scored source-checked	GLM-5.3-Flash individual evaluations ↗Observed 2026-08-26 · checked 2026-08-27
Claude Opus 4.6 (Max) as published in Qwen's Qwen3.8-Flash-Next comparison table claude-opus-4-6-max	Claude Opus 4.6	40%	text-onlysystem:qwen3-8-flash-next-comparison:cell:language:hle:4	Relative comparison · not standard direct provider-reported	Qwen3.8-Flash-Next launch and official provider evaluations ↗Observed 2026-08-26 · checked 2026-08-26
Qwen3.7-Plus (provider-published configuration) as published in Qwen's Qwen3.8-Flash-Next comparison table qwen-3-7-plus-unspecified	Qwen3.7-Plus	34.7%	text-onlysystem:qwen3-8-flash-next-comparison:cell:language:hle:2	Relative comparison · not standard direct provider-reported	Qwen3.8-Flash-Next launch and official provider evaluations ↗Observed 2026-08-26 · checked 2026-08-26
DeepSeek-V4-Flash-0731 (provider-published configuration) as published in Qwen's Qwen3.8-Flash-Next comparison table deepseek-v4-flash-0731-deepseek-0813-release-unspecified	DeepSeek V4 Flash 0731	33.8%	text-onlysystem:qwen3-8-flash-next-comparison:cell:language:hle:3	Relative comparison · not standard direct provider-reported	Qwen3.8-Flash-Next launch and official provider evaluations ↗Observed 2026-08-26 · checked 2026-08-26
Qwen3.8-27B (xhigh default thinking configuration) as published in Qwen's Qwen3.8-Flash-Next comparison table qwen-3-8-27b-xhigh	Qwen3.8-27B	30.8%	text-onlysystem:qwen3-8-flash-next-comparison:cell:language:hle:1	Relative comparison · not standard direct provider-reported	Qwen3.8-Flash-Next launch and official provider evaluations ↗Observed 2026-08-26 · checked 2026-08-26
Claude Opus 4.6 Max as published by Qwen claude-opus-4-6-max	Claude Opus 4.6	40%	text-onlyQwen3.8-27B official text table	Relative comparison · not standard direct provider-reported	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15
Qwen3.7-Plus as published by Qwen qwen-3-7-plus-unspecified	Qwen3.7-Plus	34.7%	text-onlyQwen3.8-27B official text table	Relative comparison · not standard direct provider-reported	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15
DeepSeek V4 Flash max as published by Upstage deepseek-v4-flash-max	DeepSeek V4 Flash	32.3%	without toolsSolar Open 2 card English table	Relative comparison · not standard direct provider-reported	Solar Open 2 250B model card ↗Observed 2026-08-15 · checked 2026-08-15
Qwen3.8-27B (xhigh) qwen-3-8-27b-xhigh	Qwen3.8-27B	30.8%	text-onlyQwen3.8-27B official text table	Score input provider-reported	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15
Solar Open 2 250B (high) solar-open2-250b-high	Solar Open 2 250B	28.8%	without toolsSolar Open 2 card English table	Score input provider-reported	Solar Open 2 250B model card ↗Observed 2026-08-15 · checked 2026-08-15
MiMo-V2.5 as published by Upstage mimo-v2-5-solar-open2-unspecified	MiMo-V2.5	24.3%	without toolsSolar Open 2 card English table	Relative comparison · not standard direct provider-reported	Solar Open 2 250B model card ↗Observed 2026-08-15 · checked 2026-08-15
Qwen3.6-27B as published by Qwen qwen3-6-27b-default	Qwen3.6 27B	24%	text-onlyQwen3.8-27B official text table	Relative comparison · not standard direct provider-reported	Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15
Mistral Medium 3.5 as published by Upstage mistral-medium-3-5-high	Mistral Medium 3.5	12.8%	without toolsSolar Open 2 card English table	Relative comparison · not standard direct provider-reported	Solar Open 2 250B model card ↗Observed 2026-08-15 · checked 2026-08-15
Solar Open 100B as published by Upstage solar-open-100b-reasoning-high	Solar Open 100B (Reasoning)	11.5%	without toolsSolar Open 2 card English table	Relative comparison · not standard direct provider-reported	Solar Open 2 250B model card ↗Observed 2026-08-15 · checked 2026-08-15
Command A+ as published by Upstage command-a-plus-solar-open2-unspecified	Command A+	11.4%	without toolsSolar Open 2 card English table	Relative comparison · not standard direct provider-reported	Solar Open 2 250B model card ↗Observed 2026-08-15 · checked 2026-08-15
Muse Glimmer-30B; high reasoning; temperature=1.0; top_p=0.95; top_k=64 muse-glimmer-30b-high	Muse Glimmer 30B	22%	text-only / no tools / 2,158 questionsArtificial Analysis HLE text-only evaluation	Public reference · not scored provider-reported	Muse Glimmer Evaluation Methodology ↗Observed 2026-08-10 · checked 2026-08-10
Qwen3.8 Max (xhigh, default reasoning effort) qwen-3-8-max-xhigh	Qwen3.8 Max	43.6%	CurrentQwen provider evaluation without tools	Public reference · not scored provider-reported	Qwen3.8 Max official release ↗Observed 2026-08-03 · checked 2026-08-05
Exact BenchLM registry variant Claude Opus 5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 5	64.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Claude Mythos 5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Mythos 5	64.5%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Muse Spark 1.1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Muse Spark 1.1	62.1%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5.4 Pro; bulk export does not retain a complete upstream harness configuration. gpt-5-4-pro-default-medium	GPT-5.4	58.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Claude Opus 4.8; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 4.8	57.9%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Claude Sonnet 5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Sonnet 5	57.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5.5 Pro; bulk export does not retain a complete upstream harness configuration. gpt-5-5-pro-default-high	GPT-5.5	57.2%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Kimi K3 public default configuration (reasoning_effort=max; temperature=1.0) kimi-k3-max	Kimi K3	56%	HLE-Full with general toolsMoonshot Kimi K3 model-card evaluation	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-29
Exact BenchLM registry variant Claude Opus 4.7 (Adaptive); bulk export does not retain a complete upstream harness configuration. claude-opus-4-7-max	Claude Opus 4.7	54.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GLM-5.2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-5.2	54.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Claude Fable 5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Fable 5	53.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Claude Opus 4.6; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 4.6	53%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GLM-5.1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-5.1	52.3%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.5	52.2%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5.4; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.4	52.1%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GLM-5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-5	50.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Muse Spark; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Muse Spark	50.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Claude Sonnet 4.6; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Sonnet 4.6	49%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant MiMo-V2.5-Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	MiMo-V2.5-Pro	48%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Inkling-Small; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Inkling-Small	47.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Agents-A1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Agents-A1	47.6%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5.6 Sol; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.6 Sol	47.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Inkling; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Inkling	46%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5.6 Terra; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.6 Terra	41.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5.4 mini; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.4 mini	41.5%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.7 Max; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.7-Max	41.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Grok 4.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4.5	40.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Gemini 3.5 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 3.5 Flash	40.2%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5.3 Codex; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.3-Codex	39.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Gemini 3.6 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 3.6 Flash	38.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant DeepSeek V4 Pro (Max); bulk export does not retain a complete upstream harness configuration. deepseek-v4-pro-max	DeepSeek V4 Pro	37.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5.4 nano; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.4 nano	37.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5.6 Luna; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.6 Luna	37.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant MiniMax M3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	MiniMax M3	37.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Claude Opus 4.6 (Adaptive); bulk export does not retain a complete upstream harness configuration. claude-opus-4-6-max	Claude Opus 4.6	36.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5.2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.2	35.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Grok 4.3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4.3	35%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant DeepSeek V4 Flash (Max); bulk export does not retain a complete upstream harness configuration. deepseek-v4-flash-max	DeepSeek V4 Flash	34.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Kimi K2.6; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2.6	34.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.7 Plus; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.7-Plus	34.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant DeepSeek V4 Pro (High); bulk export does not retain a complete upstream harness configuration. deepseek-v4-pro-high	DeepSeek V4 Pro	34.5%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5.2-Codex; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.2 Codex	33.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Kimi K2.7 Code; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2.7 Code	32.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Hy3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Hy3	31.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Claude Opus 4.7; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 4.7	31.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Claude Opus 4.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 4.5	30.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Kimi K2.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2.5	30.1%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant DeepSeek V4 Flash (High); bulk export does not retain a complete upstream harness configuration. deepseek-v4-flash-high	DeepSeek V4 Flash	29.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Kimi K2.5 (Reasoning); bulk export does not retain a complete upstream harness configuration. kimi-k2-5-thinking	Kimi K2.5	29.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen 3.6 Max (preview); bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen 3.6 Max (preview)	28.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.6 Plus; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.6 Plus	28.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.5 397B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5 397B A17B	28.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Claude Opus 4.5 Thinking; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 4.5 Thinking	28.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant MiMo-V2-Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	MiMo-V2-Pro	28.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant MiniMax M2.7; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	MiniMax M2.7	28.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.5 397B (Reasoning); bulk export does not retain a complete upstream harness configuration. qwen3-5-397b-thinking	Qwen3.5 397B A17B	27.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Nemotron 3 Ultra; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron 3 Ultra	26.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Gemma 4 31B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 4 31B	26.5%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5.1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.1	26.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5 (high); bulk export does not retain a complete upstream harness configuration. gpt-5-high	GPT-5	26.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Hy3 Preview; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Hy3 Preview	25.5%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GLM-5-Turbo; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-5-Turbo	25.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GLM-4.7; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-4.7	24.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.6-27B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.6 27B	24%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Grok 4; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4	23.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5 (medium); bulk export does not retain a complete upstream harness configuration. gpt-5-medium	GPT-5	23.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5.1-Codex; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.1-Codex	23.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-5.1-Codex-Max; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.1-Codex-Max	23.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.5-122B-A10B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-122B-A10B	23.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.5-27B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5 27B	22.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.6-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.6-35B-A3B	21.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant o3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	o3	20%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant MiMo-V2-Omni; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	MiMo-V2-Omni	19.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Step 3.7 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Step 3.7 Flash	19.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3.5-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-35B-A3B	19.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Gemini 2.5 Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 2.5 Pro	18.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-OSS 120B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-OSS 120B	18.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Grok 4.1 Fast (Reasoning); bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4.1 Fast (Reasoning)	17.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Gemini 3.5 Flash-Lite; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 3.5 Flash-Lite	17.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Gemma 4 26B A4B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 4 26B A4B	17.2%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Grok 4 Fast (Reasoning); bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4 Fast (Reasoning)	17%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Gemini 3.1 Flash-Lite; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 3.1 Flash-Lite	16.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GLM-5V-Turbo; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-5V-Turbo	15.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant DeepSeek-R1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek-R1	14.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Gemma 4 12B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 4 12B Unified	14.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Trinity-Large-Preview; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Trinity-Large-Preview	14.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Trinity-Large-Thinking; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Trinity-Large-Thinking	14.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Gemini 3 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 3 Flash	14.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant K-Exaone; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	K-Exaone	13.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant DeepSeek V3.1 (Reasoning); bulk export does not retain a complete upstream harness configuration. deepseek-v3-1-reasoning-default	DeepSeek V3.1	13%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Mistral Medium 3.5 128B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Mistral Medium 3.5 128B	12.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Claude 4.1 Opus Thinking; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude 4.1 Opus Thinking	11.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Command A+; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Command A+	11.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen3 Max; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3 Max	11.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant DeepSeek V3.2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek V3.2	10.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Nemotron 3 Nano 30B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron 3 Nano 30B	10.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Sarvam 105B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Sarvam 105B	10.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-OSS 20B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-OSS 20B	9.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Mistral Small 4; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Mistral Small 4	9.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Mistral Small 4 (Reasoning); bulk export does not retain a complete upstream harness configuration. mistral-small-4-reasoning	Mistral Small 4	9.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant o3-mini; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	o3-mini	8.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant DeepSeek V4 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek V4 Flash	8.1%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Nemotron Ultra 253B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron Ultra 253B	8.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant DeepSeek V4 Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek V4 Pro	7.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant o1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	o1	7.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Grok Code Fast 1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok Code Fast 1	7.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Kimi K2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2	7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Sarvam 30B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Sarvam 30B	7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant LFM2.5-8B-A1B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	LFM2.5-8B-A1B	6.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GLM-4.5-Air; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-4.5-Air	6.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Granite-4.0-H-350M; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Granite-4.0-H-350M	6.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant DeepSeek V3.1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek V3.1	6.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Ling 2.6 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Ling 2.6 Flash	6.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Exaone 4.0 1.2B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Exaone 4.0 1.2B	5.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Granite-4.0-350M; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Granite-4.0-350M	5.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant DeepSeek R1 Distill Qwen 32B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek R1 Distill Qwen 32B	5.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Nemotron 3 Nano Omni 30B A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron 3 Nano Omni 30B A3B	5.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GLM-4.6; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-4.6	5.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Gemini 2.5 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 2.5 Flash	5.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Granite-4.0-1B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Granite-4.0-1B	5.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant LFM2.5-VL-1.6B-Extract; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	LFM2.5-VL-1.6B-Extract	5.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Granite-4.0-H-1B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Granite-4.0-H-1B	5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Grok 4.1 Fast; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4.1 Fast	5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Exaone 4.0 32B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Exaone 4.0 32B	4.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Gemini 1.5 Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 1.5 Pro	4.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Gemma 4 E2B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 4 E2B	4.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Llama 4 Maverick; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Llama 4 Maverick	4.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Gemma 3 27B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 3 27B	4.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Gemini 1.0 Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 1.0 Pro	4.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-4.1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4.1	4.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-4.1 mini; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4.1 mini	4.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Llama 4 Scout; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Llama 4 Scout	4.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Mistral Medium 3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Mistral Medium 3	4.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Llama 3.1 405B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Llama 3.1 405B	4.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Mistral Large 3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Mistral Large 3	4.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Phi-4; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Phi-4	4.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Claude 4 Sonnet; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude 4 Sonnet	4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-4o mini; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4o mini	4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Mistral Large 2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Mistral Large 2	4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Claude 3 Haiku; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude 3 Haiku	3.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-4.1 nano; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4.1 nano	3.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Qwen2.5 Coder 32B Instruct; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen2.5 Coder 32B Instruct	3.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Solar Pro 2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Solar Pro 2	3.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Gemma 4 E4B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 4 E4B	3.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant DeepSeek V3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek V3	3.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Nova Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nova Pro	3.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-4 Turbo; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4 Turbo	3.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant GPT-4o; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4o	3.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Claude 3 Opus; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude 3 Opus	3.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01
Exact BenchLM registry variant Claude Opus 5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 5	64.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Claude Mythos 5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Mythos 5	64.5%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Muse Spark 1.1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Muse Spark 1.1	62.1%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5.4 Pro; bulk export does not retain a complete upstream harness configuration. gpt-5-4-pro-default-medium	GPT-5.4	58.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Claude Opus 4.8; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 4.8	57.9%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Claude Sonnet 5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Sonnet 5	57.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5.5 Pro; bulk export does not retain a complete upstream harness configuration. gpt-5-5-pro-default-high	GPT-5.5	57.2%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Kimi K3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K3	56%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Claude Opus 4.7 (Adaptive); bulk export does not retain a complete upstream harness configuration. claude-opus-4-7-max	Claude Opus 4.7	54.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GLM-5.2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-5.2	54.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Claude Fable 5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Fable 5	53.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Claude Opus 4.6; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 4.6	53%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GLM-5.1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-5.1	52.3%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.5	52.2%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5.4; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.4	52.1%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GLM-5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-5	50.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Muse Spark; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Muse Spark	50.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Claude Sonnet 4.6; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Sonnet 4.6	49%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant MiMo-V2.5-Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	MiMo-V2.5-Pro	48%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Agents-A1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Agents-A1	47.6%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5.6 Sol; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.6 Sol	47.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Inkling; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Inkling	46%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5.6 Terra; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.6 Terra	41.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5.4 mini; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.4 mini	41.5%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.7 Max; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.7-Max	41.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Grok 4.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4.5	40.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Gemini 3.5 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 3.5 Flash	40.2%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5.3 Codex; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.3-Codex	39.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Gemini 3.6 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 3.6 Flash	38.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant DeepSeek V4 Pro (Max); bulk export does not retain a complete upstream harness configuration. deepseek-v4-pro-max	DeepSeek V4 Pro	37.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5.4 nano; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.4 nano	37.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5.6 Luna; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.6 Luna	37.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant MiniMax M3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	MiniMax M3	37.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Claude Opus 4.6 (Adaptive); bulk export does not retain a complete upstream harness configuration. claude-opus-4-6-max	Claude Opus 4.6	36.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5.2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.2	35.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Grok 4.3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4.3	35%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant DeepSeek V4 Flash (Max); bulk export does not retain a complete upstream harness configuration. deepseek-v4-flash-max	DeepSeek V4 Flash	34.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Kimi K2.6; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2.6	34.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.7 Plus; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.7-Plus	34.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant DeepSeek V4 Pro (High); bulk export does not retain a complete upstream harness configuration. deepseek-v4-pro-high	DeepSeek V4 Pro	34.5%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5.2-Codex; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.2 Codex	33.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Kimi K2.7 Code; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2.7 Code	32.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Hy3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Hy3	31.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Claude Opus 4.7; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 4.7	31.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Claude Opus 4.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 4.5	30.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Kimi K2.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2.5	30.1%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant DeepSeek V4 Flash (High); bulk export does not retain a complete upstream harness configuration. deepseek-v4-flash-high	DeepSeek V4 Flash	29.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Kimi K2.5 (Reasoning); bulk export does not retain a complete upstream harness configuration. kimi-k2-5-thinking	Kimi K2.5	29.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen 3.6 Max (preview); bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen 3.6 Max (preview)	28.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.6 Plus; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.6 Plus	28.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.5 397B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5 397B A17B	28.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Claude Opus 4.5 Thinking; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 4.5 Thinking	28.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant MiMo-V2-Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	MiMo-V2-Pro	28.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant MiniMax M2.7; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	MiniMax M2.7	28.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.5 397B (Reasoning); bulk export does not retain a complete upstream harness configuration. qwen3-5-397b-thinking	Qwen3.5 397B A17B	27.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Nemotron 3 Ultra; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron 3 Ultra	26.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Gemma 4 31B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 4 31B	26.5%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5.1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.1	26.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5 (high); bulk export does not retain a complete upstream harness configuration. gpt-5-high	GPT-5	26.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Hy3 Preview; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Hy3 Preview	25.5%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GLM-5-Turbo; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-5-Turbo	25.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GLM-4.7; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-4.7	24.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.6-27B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.6 27B	24%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Grok 4; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4	23.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5 (medium); bulk export does not retain a complete upstream harness configuration. gpt-5-medium	GPT-5	23.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5.1-Codex; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.1-Codex	23.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-5.1-Codex-Max; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.1-Codex-Max	23.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.5-122B-A10B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-122B-A10B	23.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.5-27B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5 27B	22.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.6-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.6-35B-A3B	21.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant o3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	o3	20%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant MiMo-V2-Omni; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	MiMo-V2-Omni	19.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Step 3.7 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Step 3.7 Flash	19.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3.5-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-35B-A3B	19.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Gemini 2.5 Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 2.5 Pro	18.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-OSS 120B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-OSS 120B	18.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Grok 4.1 Fast (Reasoning); bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4.1 Fast (Reasoning)	17.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Gemini 3.5 Flash-Lite; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 3.5 Flash-Lite	17.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Gemma 4 26B A4B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 4 26B A4B	17.2%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Grok 4 Fast (Reasoning); bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4 Fast (Reasoning)	17%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Gemini 3.1 Flash-Lite; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 3.1 Flash-Lite	16.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GLM-5V-Turbo; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-5V-Turbo	15.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant DeepSeek-R1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek-R1	14.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Gemma 4 12B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 4 12B Unified	14.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Trinity-Large-Preview; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Trinity-Large-Preview	14.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Trinity-Large-Thinking; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Trinity-Large-Thinking	14.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Gemini 3 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 3 Flash	14.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant K-Exaone; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	K-Exaone	13.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant DeepSeek V3.1 (Reasoning); bulk export does not retain a complete upstream harness configuration. deepseek-v3-1-reasoning-default	DeepSeek V3.1	13%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Mistral Medium 3.5 128B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Mistral Medium 3.5 128B	12.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Claude 4.1 Opus Thinking; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude 4.1 Opus Thinking	11.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Command A+; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Command A+	11.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen3 Max; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3 Max	11.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant DeepSeek V3.2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek V3.2	10.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Nemotron 3 Nano 30B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron 3 Nano 30B	10.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Sarvam 105B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Sarvam 105B	10.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-OSS 20B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-OSS 20B	9.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Mistral Small 4; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Mistral Small 4	9.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Mistral Small 4 (Reasoning); bulk export does not retain a complete upstream harness configuration. mistral-small-4-reasoning	Mistral Small 4	9.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant o3-mini; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	o3-mini	8.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant DeepSeek V4 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek V4 Flash	8.1%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Nemotron Ultra 253B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron Ultra 253B	8.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant DeepSeek V4 Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek V4 Pro	7.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant o1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	o1	7.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Grok Code Fast 1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok Code Fast 1	7.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Kimi K2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2	7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Sarvam 30B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Sarvam 30B	7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant LFM2.5-8B-A1B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	LFM2.5-8B-A1B	6.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GLM-4.5-Air; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-4.5-Air	6.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Granite-4.0-H-350M; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Granite-4.0-H-350M	6.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant DeepSeek V3.1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek V3.1	6.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Ling 2.6 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Ling 2.6 Flash	6.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Exaone 4.0 1.2B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Exaone 4.0 1.2B	5.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Granite-4.0-350M; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Granite-4.0-350M	5.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant DeepSeek R1 Distill Qwen 32B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek R1 Distill Qwen 32B	5.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Nemotron 3 Nano Omni 30B A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron 3 Nano Omni 30B A3B	5.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GLM-4.6; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-4.6	5.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Gemini 2.5 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 2.5 Flash	5.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Granite-4.0-1B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Granite-4.0-1B	5.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant LFM2.5-VL-1.6B-Extract; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	LFM2.5-VL-1.6B-Extract	5.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Granite-4.0-H-1B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Granite-4.0-H-1B	5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Grok 4.1 Fast; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4.1 Fast	5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Exaone 4.0 32B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Exaone 4.0 32B	4.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Gemini 1.5 Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 1.5 Pro	4.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Gemma 4 E2B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 4 E2B	4.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Llama 4 Maverick; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Llama 4 Maverick	4.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Gemma 3 27B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 3 27B	4.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Gemini 1.0 Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 1.0 Pro	4.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-4.1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4.1	4.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-4.1 mini; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4.1 mini	4.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Llama 4 Scout; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Llama 4 Scout	4.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Mistral Medium 3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Mistral Medium 3	4.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Llama 3.1 405B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Llama 3.1 405B	4.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Mistral Large 3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Mistral Large 3	4.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Phi-4; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Phi-4	4.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Claude 4 Sonnet; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude 4 Sonnet	4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-4o mini; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4o mini	4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Mistral Large 2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Mistral Large 2	4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Claude 3 Haiku; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude 3 Haiku	3.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-4.1 nano; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4.1 nano	3.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Qwen2.5 Coder 32B Instruct; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen2.5 Coder 32B Instruct	3.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Solar Pro 2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Solar Pro 2	3.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Gemma 4 E4B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 4 E4B	3.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant DeepSeek V3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek V3	3.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Nova Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nova Pro	3.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-4 Turbo; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4 Turbo	3.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant GPT-4o; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4o	3.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Exact BenchLM registry variant Claude 3 Opus; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude 3 Opus	3.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27
Humanity's Last Exam with tools as published in the Anthropic Claude Opus 5 launch table. source label without registered configuration ID	Claude Opus 5	64.7%	CurrentAnthropic provider evaluation	Score input provider-reported	Introducing Claude Opus 5 ↗Observed 2026-07-24 · checked 2026-07-24
Exact BenchLM registry variant Claude Mythos 5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Mythos 5	64.5%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Muse Spark 1.1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Muse Spark 1.1	62.1%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5.4 Pro; bulk export does not retain a complete upstream harness configuration. gpt-5-4-pro-default-medium	GPT-5.4	58.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Claude Opus 4.8; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 4.8	57.9%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Claude Sonnet 5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Sonnet 5	57.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5.5 Pro; bulk export does not retain a complete upstream harness configuration. gpt-5-5-pro-default-high	GPT-5.5	57.2%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Kimi K3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K3	56%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Claude Opus 4.7 (Adaptive); bulk export does not retain a complete upstream harness configuration. claude-opus-4-7-max	Claude Opus 4.7	54.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GLM-5.2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-5.2	54.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Claude Fable 5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Fable 5	53.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Claude Opus 4.6; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 4.6	53%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GLM-5.1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-5.1	52.3%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.5	52.2%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5.4; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.4	52.1%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GLM-5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-5	50.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Muse Spark; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Muse Spark	50.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Claude Sonnet 4.6; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Sonnet 4.6	49%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant MiMo-V2.5-Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	MiMo-V2.5-Pro	48%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Agents-A1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Agents-A1	47.6%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5.6 Sol; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.6 Sol	47.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Inkling; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Inkling	46%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5.6 Terra; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.6 Terra	41.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5.4 mini; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.4 mini	41.5%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.7 Max; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.7-Max	41.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Grok 4.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4.5	40.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Gemini 3.5 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 3.5 Flash	40.2%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5.3 Codex; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.3-Codex	39.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Gemini 3.6 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 3.6 Flash	38.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Artificial Analysis Humanity's Last Exam independent evaluation. source label without registered configuration ID	Gemini 3.6 Flash	38.3%	CurrentArtificial Analysis evaluation harness	Public reference · not scored source-checked	Gemini 3.6 Flash (Artificial Analysis) ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant DeepSeek V4 Pro (Max); bulk export does not retain a complete upstream harness configuration. deepseek-v4-pro-max	DeepSeek V4 Pro	37.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5.4 nano; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.4 nano	37.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5.6 Luna; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.6 Luna	37.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant MiniMax M3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	MiniMax M3	37.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Claude Opus 4.6 (Adaptive); bulk export does not retain a complete upstream harness configuration. claude-opus-4-6-max	Claude Opus 4.6	36.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5.2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.2	35.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Grok 4.3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4.3	35%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant DeepSeek V4 Flash (Max); bulk export does not retain a complete upstream harness configuration. deepseek-v4-flash-max	DeepSeek V4 Flash	34.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Kimi K2.6; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2.6	34.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.7 Plus; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.7-Plus	34.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant DeepSeek V4 Pro (High); bulk export does not retain a complete upstream harness configuration. deepseek-v4-pro-high	DeepSeek V4 Pro	34.5%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5.2-Codex; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.2 Codex	33.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Kimi K2.7 Code; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2.7 Code	32.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Hy3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Hy3	31.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Claude Opus 4.7; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 4.7	31.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Claude Opus 4.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 4.5	30.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Kimi K2.5; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2.5	30.1%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant DeepSeek V4 Flash (High); bulk export does not retain a complete upstream harness configuration. deepseek-v4-flash-high	DeepSeek V4 Flash	29.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Kimi K2.5 (Reasoning); bulk export does not retain a complete upstream harness configuration. kimi-k2-5-thinking	Kimi K2.5	29.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen 3.6 Max (preview); bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen 3.6 Max (preview)	28.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.6 Plus; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.6 Plus	28.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.5 397B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5 397B A17B	28.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Claude Opus 4.5 Thinking; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude Opus 4.5 Thinking	28.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant MiMo-V2-Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	MiMo-V2-Pro	28.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant MiniMax M2.7; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	MiniMax M2.7	28.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.5 397B (Reasoning); bulk export does not retain a complete upstream harness configuration. qwen3-5-397b-thinking	Qwen3.5 397B A17B	27.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Nemotron 3 Ultra; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron 3 Ultra	26.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Gemma 4 31B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 4 31B	26.5%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5.1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.1	26.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5 (high); bulk export does not retain a complete upstream harness configuration. gpt-5-high	GPT-5	26.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Hy3 Preview; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Hy3 Preview	25.5%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GLM-5-Turbo; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-5-Turbo	25.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GLM-4.7; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-4.7	24.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.6-27B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.6 27B	24%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Grok 4; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4	23.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5 (medium); bulk export does not retain a complete upstream harness configuration. gpt-5-medium	GPT-5	23.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5.1-Codex; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.1-Codex	23.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-5.1-Codex-Max; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-5.1-Codex-Max	23.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.5-122B-A10B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-122B-A10B	23.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.5-27B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5 27B	22.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.6-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.6-35B-A3B	21.4%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant o3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	o3	20%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant MiMo-V2-Omni; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	MiMo-V2-Omni	19.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Step 3.7 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Step 3.7 Flash	19.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3.5-35B-A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3.5-35B-A3B	19.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Gemini 2.5 Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 2.5 Pro	18.8%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-OSS 120B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-OSS 120B	18.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Grok 4.1 Fast (Reasoning); bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4.1 Fast (Reasoning)	17.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Gemini 3.5 Flash-Lite; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 3.5 Flash-Lite	17.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Artificial Analysis Humanity's Last Exam independent evaluation. source label without registered configuration ID	Gemini 3.5 Flash-Lite	17.5%	CurrentArtificial Analysis evaluation harness	Public reference · not scored source-checked	Gemini 3.5 Flash-Lite (Artificial Analysis) ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Gemma 4 26B A4B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 4 26B A4B	17.2%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Grok 4 Fast (Reasoning); bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4 Fast (Reasoning)	17%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Gemini 3.1 Flash-Lite; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 3.1 Flash-Lite	16.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GLM-5V-Turbo; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-5V-Turbo	15.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant DeepSeek-R1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek-R1	14.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Gemma 4 12B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 4 12B Unified	14.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Trinity-Large-Preview; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Trinity-Large-Preview	14.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Trinity-Large-Thinking; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Trinity-Large-Thinking	14.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Gemini 3 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 3 Flash	14.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant K-Exaone; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	K-Exaone	13.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant DeepSeek V3.1 (Reasoning); bulk export does not retain a complete upstream harness configuration. deepseek-v3-1-reasoning-default	DeepSeek V3.1	13%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Mistral Medium 3.5 128B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Mistral Medium 3.5 128B	12.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Claude 4.1 Opus Thinking; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude 4.1 Opus Thinking	11.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Command A+; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Command A+	11.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen3 Max; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen3 Max	11.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant DeepSeek V3.2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek V3.2	10.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Nemotron 3 Nano 30B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron 3 Nano 30B	10.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Sarvam 105B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Sarvam 105B	10.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-OSS 20B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-OSS 20B	9.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Mistral Small 4; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Mistral Small 4	9.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Mistral Small 4 (Reasoning); bulk export does not retain a complete upstream harness configuration. mistral-small-4-reasoning	Mistral Small 4	9.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant o3-mini; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	o3-mini	8.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant DeepSeek V4 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek V4 Flash	8.1%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Nemotron Ultra 253B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron Ultra 253B	8.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant DeepSeek V4 Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek V4 Pro	7.7%	2025Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant o1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	o1	7.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Grok Code Fast 1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok Code Fast 1	7.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Kimi K2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Kimi K2	7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Sarvam 30B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Sarvam 30B	7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant LFM2.5-8B-A1B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	LFM2.5-8B-A1B	6.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GLM-4.5-Air; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-4.5-Air	6.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Granite-4.0-H-350M; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Granite-4.0-H-350M	6.4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant DeepSeek V3.1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek V3.1	6.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Ling 2.6 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Ling 2.6 Flash	6.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Exaone 4.0 1.2B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Exaone 4.0 1.2B	5.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Granite-4.0-350M; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Granite-4.0-350M	5.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant DeepSeek R1 Distill Qwen 32B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	DeepSeek R1 Distill Qwen 32B	5.5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Nemotron 3 Nano Omni 30B A3B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Nemotron 3 Nano Omni 30B A3B	5.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GLM-4.6; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GLM-4.6	5.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Gemini 2.5 Flash; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 2.5 Flash	5.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Granite-4.0-1B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Granite-4.0-1B	5.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant LFM2.5-VL-1.6B-Extract; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	LFM2.5-VL-1.6B-Extract	5.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Granite-4.0-H-1B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Granite-4.0-H-1B	5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Grok 4.1 Fast; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Grok 4.1 Fast	5%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Exaone 4.0 32B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Exaone 4.0 32B	4.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Gemini 1.5 Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 1.5 Pro	4.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Gemma 4 E2B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 4 E2B	4.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Llama 4 Maverick; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Llama 4 Maverick	4.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Gemma 3 27B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 3 27B	4.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Gemini 1.0 Pro; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemini 1.0 Pro	4.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-4.1; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4.1	4.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-4.1 mini; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4.1 mini	4.6%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Llama 4 Scout; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Llama 4 Scout	4.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Mistral Medium 3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Mistral Medium 3	4.3%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Llama 3.1 405B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Llama 3.1 405B	4.2%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Mistral Large 3; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Mistral Large 3	4.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Phi-4; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Phi-4	4.1%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Claude 4 Sonnet; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude 4 Sonnet	4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-4o mini; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4o mini	4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Mistral Large 2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Mistral Large 2	4%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Claude 3 Haiku; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Claude 3 Haiku	3.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant GPT-4.1 nano; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	GPT-4.1 nano	3.9%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Qwen2.5 Coder 32B Instruct; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Qwen2.5 Coder 32B Instruct	3.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Solar Pro 2; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Solar Pro 2	3.8%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21
Exact BenchLM registry variant Gemma 4 E4B; bulk export does not retain a complete upstream harness configuration. source label without registered configuration ID	Gemma 4 E4B	3.7%	2026Source-native system	Source carrier · no additional scoring weight source-checked	BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact published model / configuration

Canonical product

Score

Version / system

Evidence

Source / observed

Claude Opus 4.7 (Adaptive Reasoning, Max Effort) (Artificial Analysis independent run)

claude-opus-4-7-max

42.3%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

Claude Opus 4.7 (Adaptive Reasoning, Max Effort) individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29

GLM-5.2 (max) (Artificial Analysis independent run)

glm-5-2-max

41.1%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

GLM-5.2 (max) individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29

Claude Opus 4.6 (Adaptive Reasoning, Max Effort) (Artificial Analysis independent run)

claude-opus-4-6-max

39.9%

text-only currentArtificial Analysis text-only HLE evaluation

Public reference · not scored

independently-verified

Claude Opus 4.6 (Adaptive Reasoning, Max Effort) individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29

Qwen3.8-Flash-Next (Artificial Analysis independent run)

qwen-3-8-flash-next-aa-unspecified

Qwen3.8-Flash-Next

38.0%

text-only currentArtificial Analysis text-only HLE evaluation

Public reference · not scored

independently-verified

Qwen3.8-Flash-Next individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29

LongCat 2.0 (Artificial Analysis independent run)

longcat-2-0-default

LongCat-2.0

33.7%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

LongCat 2.0 individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29

Kimi K2.5 (Reasoning) (Artificial Analysis completed independent run)

kimi-k2-5-thinking

30.7%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

Kimi K2.5 (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29

Qwen3.5 397B A17B (Reasoning) (Artificial Analysis completed independent run)

qwen3-5-397b-thinking

29.0%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

Qwen3.5 397B A17B (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29

Qwen3.5 122B A10B (Reasoning) (Artificial Analysis completed independent run)

qwen3-5-122b-a10b-aa-reasoning-default

25.2%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

Qwen3.5 122B A10B (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29

Qwen3.6 35B A3B (Reasoning) (Artificial Analysis completed independent run)

qwen3-6-35b-a3b-aa-reasoning-default

22.2%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

Qwen3.6 35B A3B (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29

Gemma 4 26B A4B (Reasoning) (Artificial Analysis completed independent run)

gemma-4-26b-a4b-aa-reasoning-default

19.3%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

Gemma 4 26B A4B (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29

Trinity Large Thinking (Artificial Analysis completed independent run)

trinity-large-thinking-aa-reasoning-default

15.8%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

Trinity Large Thinking current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29

DeepSeek V3.1 (Reasoning) (Artificial Analysis independent run)

deepseek-v3-1-reasoning-default

14.3%

text-only currentArtificial Analysis text-only HLE evaluation

Public reference · not scored

independently-verified

DeepSeek V3.1 (Reasoning) individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29

Mistral Medium 3.5 (Artificial Analysis completed independent run)

mistral-medium-3-5-128b-aa-reasoning-default

13.8%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

Mistral Medium 3.5 current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29

NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) (Artificial Analysis completed independent run)

nemotron-3-nano-30b-aa-reasoning-default

11.4%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29

Mistral Small 4 (Reasoning) (Artificial Analysis completed independent run)

mistral-small-4-reasoning

9.9%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

Mistral Small 4 (Reasoning) current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29

DeepSeek V3.1 (Non-reasoning) (Artificial Analysis independent run)

deepseek-v3-1-non-reasoning

6.7%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

DeepSeek V3.1 (Non-reasoning) individual evaluations ↗Observed 2026-08-29 · checked 2026-08-29

GPT-4.1 mini (Artificial Analysis completed independent run)

gpt-4-1-mini-epoch-gpt-4-1-mini-2025-04-14

5.0%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

GPT-4.1 mini current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29

Llama 4 Maverick (Artificial Analysis completed independent run)

llama-4-maverick-aa-non-reasoning-default

4.9%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

Llama 4 Maverick current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29

Gemma 3 27B Instruct (Artificial Analysis completed independent run)

gemma-3-27b-aa-non-reasoning-default

4.4%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

Gemma 3 27B Instruct current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29

Llama 4 Scout (Artificial Analysis completed independent run)

llama-4-scout-aa-non-reasoning-default

3.8%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

Llama 4 Scout current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29

GPT-4.1 nano (Artificial Analysis completed independent run)

gpt-4-1-nano-epoch-gpt-4-1-nano-2025-04-14

3.8%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

GPT-4.1 nano current model and individual-evaluation page ↗Observed 2026-08-29 · checked 2026-08-29

Claude Fable 5 (max; Artificial Analysis independent run)

claude-fable-5-max

55.5%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

Claude Fable 5 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

Claude Opus 5 (max; Artificial Analysis independent run)

claude-opus-5-max

54.9%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

Claude Opus 5 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

GPT-5.6 Sol (max; Artificial Analysis independent run)

gpt-5-6-sol-max

49.5%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

GPT-5.6 Sol individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

Claude Opus 4.8 (max; Artificial Analysis independent run)

claude-opus-4-8-max

48.7%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

Claude Opus 4.8 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

Kimi K3 (max; Artificial Analysis independent run)

kimi-k3-max

46.9%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

Kimi K3 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

Muse Spark 1.1 (xhigh; Artificial Analysis independent run)

muse-spark-1-1-xhigh

46.2%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

Muse Spark 1.1 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

GPT-5.5 (xhigh; Artificial Analysis independent run)

gpt-5-5-xhigh

45.8%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

GPT-5.5 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

Muse Spark 1.2 (xhigh; Artificial Analysis independent run)

muse-spark-1-2-xhigh

Muse Spark 1.2

45.5%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

Muse Spark 1.2 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

GPT-5.4 (xhigh; Artificial Analysis independent run)

gpt-5-4-xhigh

43.7%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

GPT-5.4 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

GPT-5.6 Terra (max; Artificial Analysis independent run)

gpt-5-6-terra-max

42.9%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

GPT-5.6 Terra individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

Grok 4.6 (high; Artificial Analysis independent run)

grok-4-6-high

Grok 4.6

42.9%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

Grok 4.6 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

Grok 4.5 (high; Artificial Analysis independent run)

grok-4-5-aa-2-high

42.7%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

Grok 4.5 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

GLM-5.3 (max; Artificial Analysis independent run)

glm-5-3-max

GLM-5.3

42.3%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

GLM-5.3 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

Claude Sonnet 5 (max; Artificial Analysis independent run)

claude-sonnet-5-max

41.3%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

Claude Sonnet 5 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

DeepSeek V4 Pro 0813 (max; Artificial Analysis independent run)

deepseek-v4-pro-0813-max

DeepSeek V4 Pro 0813

41.0%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Public reference · not scored

independently-verified

DeepSeek V4 Pro 0813 individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

Gemini 3.6 Flash (high; Artificial Analysis independent run)

gemini-3-6-flash-high

40.8%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

Gemini 3.6 Flash individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

GLM-5.3-Flash (max; Artificial Analysis independent run)

glm-5-3-flash-max

GLM-5.3-Flash

39.9%

text-only currentArtificial Analysis text-only HLE evaluation

Score input

independently-verified

GLM-5.3-Flash individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

GPT-5.6 Luna (max; Artificial Analysis independent run)

gpt-5-6-luna-max

DeepSeek V4 Flash Vision Exp

39.5%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

GPT-5.6 Luna individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

Gemini 3.7 Flash (medium; Artificial Analysis independent run)

gemini-3-7-flash-medium

Gemini 3.7 Flash

39.0%

text-only currentArtificial Analysis text-only Humanity's Last Exam evaluation

Score input

independently-verified

Gemini 3.7 Flash individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

DeepSeek V4 Flash Vision Exp (max; Artificial Analysis independent run)

deepseek-v4-flash-vision-exp-max-harness

34.5%

text-only currentArtificial Analysis text-only HLE evaluation

Public reference · not scored

independently-verified

DeepSeek V4 Flash Vision Exp individual evaluations ↗Observed 2026-08-27 · checked 2026-08-27

GLM-5.3-Flash (max effort, documented default)

glm-5-3-flash-max

GLM-5.3-Flash

55.3%

rollingsystem:glm-5-3-flash-launch:hle-tools:0

Public reference · not scored

source-checked

GLM-5.3-Flash individual evaluations ↗Observed 2026-08-26 · checked 2026-08-27

Claude Opus 4.6 (Max) as published in Qwen's Qwen3.8-Flash-Next comparison table

claude-opus-4-6-max

40%

text-onlysystem:qwen3-8-flash-next-comparison:cell:language:hle:4

Relative comparison · not standard direct

provider-reported

Qwen3.8-Flash-Next launch and official provider evaluations ↗Observed 2026-08-26 · checked 2026-08-26

Qwen3.7-Plus (provider-published configuration) as published in Qwen's Qwen3.8-Flash-Next comparison table

qwen-3-7-plus-unspecified

34.7%

text-onlysystem:qwen3-8-flash-next-comparison:cell:language:hle:2

Relative comparison · not standard direct

provider-reported

Qwen3.8-Flash-Next launch and official provider evaluations ↗Observed 2026-08-26 · checked 2026-08-26

DeepSeek-V4-Flash-0731 (provider-published configuration) as published in Qwen's Qwen3.8-Flash-Next comparison table

deepseek-v4-flash-0731-deepseek-0813-release-unspecified

DeepSeek V4 Flash 0731

33.8%

text-onlysystem:qwen3-8-flash-next-comparison:cell:language:hle:3

Relative comparison · not standard direct

provider-reported

Qwen3.8-Flash-Next launch and official provider evaluations ↗Observed 2026-08-26 · checked 2026-08-26

Qwen3.8-27B (xhigh default thinking configuration) as published in Qwen's Qwen3.8-Flash-Next comparison table

qwen-3-8-27b-xhigh

Qwen3.8-27B

30.8%

text-onlysystem:qwen3-8-flash-next-comparison:cell:language:hle:1

Relative comparison · not standard direct

provider-reported

Qwen3.8-Flash-Next launch and official provider evaluations ↗Observed 2026-08-26 · checked 2026-08-26

Claude Opus 4.6 Max as published by Qwen

claude-opus-4-6-max

40%

text-onlyQwen3.8-27B official text table

Relative comparison · not standard direct

provider-reported

Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15

Qwen3.7-Plus as published by Qwen

qwen-3-7-plus-unspecified

34.7%

text-onlyQwen3.8-27B official text table

Relative comparison · not standard direct

provider-reported

Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15

DeepSeek V4 Flash max as published by Upstage

deepseek-v4-flash-max

32.3%

without toolsSolar Open 2 card English table

Relative comparison · not standard direct

provider-reported

Solar Open 2 250B model card ↗Observed 2026-08-15 · checked 2026-08-15

Qwen3.8-27B (xhigh)

qwen-3-8-27b-xhigh

Qwen3.8-27B

30.8%

text-onlyQwen3.8-27B official text table

Score input

provider-reported

Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15

Solar Open 2 250B (high)

solar-open2-250b-high

Solar Open 2 250B

28.8%

without toolsSolar Open 2 card English table

Score input

provider-reported

Solar Open 2 250B model card ↗Observed 2026-08-15 · checked 2026-08-15

MiMo-V2.5 as published by Upstage

mimo-v2-5-solar-open2-unspecified

MiMo-V2.5

24.3%

without toolsSolar Open 2 card English table

Relative comparison · not standard direct

provider-reported

Solar Open 2 250B model card ↗Observed 2026-08-15 · checked 2026-08-15

Qwen3.6-27B as published by Qwen

qwen3-6-27b-default

Solar Open 100B (Reasoning)

24%

text-onlyQwen3.8-27B official text table

Relative comparison · not standard direct

provider-reported

Qwen3.8-27B official model card ↗Observed 2026-08-15 · checked 2026-08-15

Mistral Medium 3.5 as published by Upstage

mistral-medium-3-5-high

Mistral Medium 3.5

12.8%

without toolsSolar Open 2 card English table

Relative comparison · not standard direct

provider-reported

Solar Open 2 250B model card ↗Observed 2026-08-15 · checked 2026-08-15

Solar Open 100B as published by Upstage

solar-open-100b-reasoning-high

11.5%

without toolsSolar Open 2 card English table

Relative comparison · not standard direct

provider-reported

Solar Open 2 250B model card ↗Observed 2026-08-15 · checked 2026-08-15

Command A+ as published by Upstage

command-a-plus-solar-open2-unspecified

11.4%

without toolsSolar Open 2 card English table

Relative comparison · not standard direct

provider-reported

Solar Open 2 250B model card ↗Observed 2026-08-15 · checked 2026-08-15

Muse Glimmer-30B; high reasoning; temperature=1.0; top_p=0.95; top_k=64

muse-glimmer-30b-high

Muse Glimmer 30B

22%

text-only / no tools / 2,158 questionsArtificial Analysis HLE text-only evaluation

Public reference · not scored

provider-reported

Muse Glimmer Evaluation Methodology ↗Observed 2026-08-10 · checked 2026-08-10

Qwen3.8 Max (xhigh, default reasoning effort)

qwen-3-8-max-xhigh

Qwen3.8 Max

43.6%

CurrentQwen provider evaluation without tools

Public reference · not scored

provider-reported

Qwen3.8 Max official release ↗Observed 2026-08-03 · checked 2026-08-05

Exact BenchLM registry variant Claude Opus 5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

64.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Claude Mythos 5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

64.5%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Muse Spark 1.1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

62.1%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5.4 Pro; bulk export does not retain a complete upstream harness configuration.

gpt-5-4-pro-default-medium

58.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Claude Opus 4.8; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

57.9%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Claude Sonnet 5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

57.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5.5 Pro; bulk export does not retain a complete upstream harness configuration.

gpt-5-5-pro-default-high

57.2%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Kimi K3 public default configuration (reasoning_effort=max; temperature=1.0)

kimi-k3-max

56%

HLE-Full with general toolsMoonshot Kimi K3 model-card evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-29

Exact BenchLM registry variant Claude Opus 4.7 (Adaptive); bulk export does not retain a complete upstream harness configuration.

claude-opus-4-7-max

54.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GLM-5.2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

54.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Claude Fable 5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

53.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Claude Opus 4.6; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

53%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GLM-5.1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

52.3%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5.5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

52.2%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5.4; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

52.1%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GLM-5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

50.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Muse Spark; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

50.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Claude Sonnet 4.6; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

49%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant MiMo-V2.5-Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

48%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Inkling-Small; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

Inkling-Small

47.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Agents-A1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

47.6%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5.6 Sol; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

47.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Inkling; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

46%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5.6 Terra; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

41.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5.4 mini; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

41.5%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Qwen3.7 Max; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

41.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Grok 4.5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

40.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Gemini 3.5 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

40.2%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5.3 Codex; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

39.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Gemini 3.6 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

38.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant DeepSeek V4 Pro (Max); bulk export does not retain a complete upstream harness configuration.

deepseek-v4-pro-max

37.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5.4 nano; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

37.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5.6 Luna; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

37.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant MiniMax M3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

37.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Claude Opus 4.6 (Adaptive); bulk export does not retain a complete upstream harness configuration.

claude-opus-4-6-max

36.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5.2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

35.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Grok 4.3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

35%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant DeepSeek V4 Flash (Max); bulk export does not retain a complete upstream harness configuration.

deepseek-v4-flash-max

34.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Kimi K2.6; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

34.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Qwen3.7 Plus; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

34.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant DeepSeek V4 Pro (High); bulk export does not retain a complete upstream harness configuration.

deepseek-v4-pro-high

34.5%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5.2-Codex; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

33.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Kimi K2.7 Code; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

32.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Hy3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

31.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Claude Opus 4.7; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

31.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Claude Opus 4.5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

30.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Kimi K2.5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

30.1%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant DeepSeek V4 Flash (High); bulk export does not retain a complete upstream harness configuration.

deepseek-v4-flash-high

29.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Kimi K2.5 (Reasoning); bulk export does not retain a complete upstream harness configuration.

kimi-k2-5-thinking

29.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Qwen 3.6 Max (preview); bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Qwen3.6 Plus; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Qwen3.5 397B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Claude Opus 4.5 Thinking; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant MiMo-V2-Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant MiniMax M2.7; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Qwen3.5 397B (Reasoning); bulk export does not retain a complete upstream harness configuration.

qwen3-5-397b-thinking

27.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Nemotron 3 Ultra; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

26.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Gemma 4 31B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

26.5%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5.1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

26.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5 (high); bulk export does not retain a complete upstream harness configuration.

gpt-5-high

26.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Hy3 Preview; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

25.5%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GLM-5-Turbo; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

25.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GLM-4.7; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

24.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Qwen3.6-27B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

24%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Grok 4; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

23.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5 (medium); bulk export does not retain a complete upstream harness configuration.

gpt-5-medium

23.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5.1-Codex; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

23.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-5.1-Codex-Max; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

23.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Qwen3.5-122B-A10B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

23.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Qwen3.5-27B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

22.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Qwen3.6-35B-A3B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

21.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant o3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

20%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant MiMo-V2-Omni; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

19.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Step 3.7 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

19.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Qwen3.5-35B-A3B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

19.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Gemini 2.5 Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

18.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-OSS 120B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

18.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Grok 4.1 Fast (Reasoning); bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

17.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Gemini 3.5 Flash-Lite; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

17.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Gemma 4 26B A4B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

17.2%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Grok 4 Fast (Reasoning); bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

17%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Gemini 3.1 Flash-Lite; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

16.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GLM-5V-Turbo; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

15.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant DeepSeek-R1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

14.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Gemma 4 12B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

14.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Trinity-Large-Preview; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

14.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Trinity-Large-Thinking; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

14.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Gemini 3 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

14.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant K-Exaone; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

13.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant DeepSeek V3.1 (Reasoning); bulk export does not retain a complete upstream harness configuration.

deepseek-v3-1-reasoning-default

13%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Mistral Medium 3.5 128B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

12.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Claude 4.1 Opus Thinking; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

11.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Command A+; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

11.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Qwen3 Max; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

11.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant DeepSeek V3.2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

10.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Nemotron 3 Nano 30B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

10.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Sarvam 105B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

10.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-OSS 20B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

9.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Mistral Small 4; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

9.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Mistral Small 4 (Reasoning); bulk export does not retain a complete upstream harness configuration.

mistral-small-4-reasoning

9.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant o3-mini; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

8.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant DeepSeek V4 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

8.1%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Nemotron Ultra 253B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

8.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant DeepSeek V4 Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

7.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant o1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

7.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Grok Code Fast 1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

7.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Kimi K2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Sarvam 30B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant LFM2.5-8B-A1B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

6.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GLM-4.5-Air; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

6.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Granite-4.0-H-350M; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

6.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant DeepSeek V3.1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

6.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Ling 2.6 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

6.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Exaone 4.0 1.2B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Granite-4.0-350M; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant DeepSeek R1 Distill Qwen 32B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Nemotron 3 Nano Omni 30B A3B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GLM-4.6; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Gemini 2.5 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Granite-4.0-1B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant LFM2.5-VL-1.6B-Extract; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Granite-4.0-H-1B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Grok 4.1 Fast; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Exaone 4.0 32B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Gemini 1.5 Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Gemma 4 E2B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Llama 4 Maverick; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Gemma 3 27B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Gemini 1.0 Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-4.1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-4.1 mini; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Llama 4 Scout; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Mistral Medium 3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Llama 3.1 405B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Mistral Large 3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Phi-4; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Claude 4 Sonnet; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-4o mini; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Mistral Large 2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Claude 3 Haiku; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-4.1 nano; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Qwen2.5 Coder 32B Instruct; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Solar Pro 2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Gemma 4 E4B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant DeepSeek V3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Nova Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-4 Turbo; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant GPT-4o; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Claude 3 Opus; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-08-01 ↗Observed 2026-08-01 · checked 2026-08-01

Exact BenchLM registry variant Claude Opus 5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

64.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Claude Mythos 5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

64.5%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Muse Spark 1.1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

62.1%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5.4 Pro; bulk export does not retain a complete upstream harness configuration.

gpt-5-4-pro-default-medium

58.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Claude Opus 4.8; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

57.9%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Claude Sonnet 5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

57.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5.5 Pro; bulk export does not retain a complete upstream harness configuration.

gpt-5-5-pro-default-high

57.2%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Kimi K3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

56%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Claude Opus 4.7 (Adaptive); bulk export does not retain a complete upstream harness configuration.

claude-opus-4-7-max

54.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GLM-5.2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

54.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Claude Fable 5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

53.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Claude Opus 4.6; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

53%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GLM-5.1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

52.3%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5.5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

52.2%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5.4; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

52.1%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GLM-5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

50.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Muse Spark; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

50.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Claude Sonnet 4.6; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

49%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant MiMo-V2.5-Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

48%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Agents-A1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

47.6%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5.6 Sol; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

47.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Inkling; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

46%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5.6 Terra; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

41.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5.4 mini; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

41.5%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Qwen3.7 Max; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

41.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Grok 4.5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

40.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Gemini 3.5 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

40.2%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5.3 Codex; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

39.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Gemini 3.6 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

38.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant DeepSeek V4 Pro (Max); bulk export does not retain a complete upstream harness configuration.

deepseek-v4-pro-max

37.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5.4 nano; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

37.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5.6 Luna; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

37.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant MiniMax M3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

37.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Claude Opus 4.6 (Adaptive); bulk export does not retain a complete upstream harness configuration.

claude-opus-4-6-max

36.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5.2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

35.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Grok 4.3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

35%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant DeepSeek V4 Flash (Max); bulk export does not retain a complete upstream harness configuration.

deepseek-v4-flash-max

34.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Kimi K2.6; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

34.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Qwen3.7 Plus; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

34.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant DeepSeek V4 Pro (High); bulk export does not retain a complete upstream harness configuration.

deepseek-v4-pro-high

34.5%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5.2-Codex; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

33.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Kimi K2.7 Code; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

32.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Hy3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

31.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Claude Opus 4.7; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

31.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Claude Opus 4.5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

30.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Kimi K2.5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

30.1%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant DeepSeek V4 Flash (High); bulk export does not retain a complete upstream harness configuration.

deepseek-v4-flash-high

29.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Kimi K2.5 (Reasoning); bulk export does not retain a complete upstream harness configuration.

kimi-k2-5-thinking

29.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Qwen 3.6 Max (preview); bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Qwen3.6 Plus; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Qwen3.5 397B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Claude Opus 4.5 Thinking; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant MiMo-V2-Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant MiniMax M2.7; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Qwen3.5 397B (Reasoning); bulk export does not retain a complete upstream harness configuration.

qwen3-5-397b-thinking

27.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Nemotron 3 Ultra; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

26.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Gemma 4 31B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

26.5%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5.1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

26.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5 (high); bulk export does not retain a complete upstream harness configuration.

gpt-5-high

26.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Hy3 Preview; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

25.5%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GLM-5-Turbo; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

25.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GLM-4.7; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

24.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Qwen3.6-27B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

24%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Grok 4; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

23.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5 (medium); bulk export does not retain a complete upstream harness configuration.

gpt-5-medium

23.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5.1-Codex; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

23.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-5.1-Codex-Max; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

23.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Qwen3.5-122B-A10B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

23.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Qwen3.5-27B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

22.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Qwen3.6-35B-A3B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

21.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant o3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

20%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant MiMo-V2-Omni; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

19.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Step 3.7 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

19.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Qwen3.5-35B-A3B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

19.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Gemini 2.5 Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

18.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-OSS 120B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

18.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Grok 4.1 Fast (Reasoning); bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

17.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Gemini 3.5 Flash-Lite; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

17.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Gemma 4 26B A4B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

17.2%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Grok 4 Fast (Reasoning); bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

17%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Gemini 3.1 Flash-Lite; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

16.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GLM-5V-Turbo; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

15.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant DeepSeek-R1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

14.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Gemma 4 12B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

14.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Trinity-Large-Preview; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

14.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Trinity-Large-Thinking; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

14.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Gemini 3 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

14.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant K-Exaone; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

13.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant DeepSeek V3.1 (Reasoning); bulk export does not retain a complete upstream harness configuration.

deepseek-v3-1-reasoning-default

13%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Mistral Medium 3.5 128B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

12.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Claude 4.1 Opus Thinking; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

11.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Command A+; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

11.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Qwen3 Max; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

11.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant DeepSeek V3.2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

10.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Nemotron 3 Nano 30B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

10.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Sarvam 105B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

10.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-OSS 20B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

9.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Mistral Small 4; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

9.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Mistral Small 4 (Reasoning); bulk export does not retain a complete upstream harness configuration.

mistral-small-4-reasoning

9.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant o3-mini; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

8.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant DeepSeek V4 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

8.1%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Nemotron Ultra 253B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

8.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant DeepSeek V4 Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

7.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant o1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

7.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Grok Code Fast 1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

7.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Kimi K2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Sarvam 30B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant LFM2.5-8B-A1B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

6.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GLM-4.5-Air; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

6.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Granite-4.0-H-350M; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

6.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant DeepSeek V3.1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

6.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Ling 2.6 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

6.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Exaone 4.0 1.2B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Granite-4.0-350M; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant DeepSeek R1 Distill Qwen 32B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Nemotron 3 Nano Omni 30B A3B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GLM-4.6; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Gemini 2.5 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Granite-4.0-1B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant LFM2.5-VL-1.6B-Extract; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Granite-4.0-H-1B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Grok 4.1 Fast; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Exaone 4.0 32B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Gemini 1.5 Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Gemma 4 E2B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Llama 4 Maverick; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Gemma 3 27B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Gemini 1.0 Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-4.1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-4.1 mini; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Llama 4 Scout; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Mistral Medium 3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Llama 3.1 405B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Mistral Large 3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Phi-4; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Claude 4 Sonnet; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-4o mini; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Mistral Large 2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Claude 3 Haiku; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-4.1 nano; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Qwen2.5 Coder 32B Instruct; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Solar Pro 2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Gemma 4 E4B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant DeepSeek V3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Nova Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-4 Turbo; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant GPT-4o; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Exact BenchLM registry variant Claude 3 Opus; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 2026-07-27 ↗Observed 2026-07-27 · checked 2026-07-27

Humanity's Last Exam with tools as published in the Anthropic Claude Opus 5 launch table.

source label without registered configuration ID

64.7%

CurrentAnthropic provider evaluation

Score input

provider-reported

Introducing Claude Opus 5 ↗Observed 2026-07-24 · checked 2026-07-24

Exact BenchLM registry variant Claude Mythos 5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

64.5%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Muse Spark 1.1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

62.1%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5.4 Pro; bulk export does not retain a complete upstream harness configuration.

gpt-5-4-pro-default-medium

58.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Claude Opus 4.8; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

57.9%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Claude Sonnet 5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

57.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5.5 Pro; bulk export does not retain a complete upstream harness configuration.

gpt-5-5-pro-default-high

57.2%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Kimi K3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

56%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Claude Opus 4.7 (Adaptive); bulk export does not retain a complete upstream harness configuration.

claude-opus-4-7-max

54.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GLM-5.2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

54.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Claude Fable 5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

53.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Claude Opus 4.6; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

53%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GLM-5.1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

52.3%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5.5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

52.2%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5.4; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

52.1%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GLM-5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

50.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Muse Spark; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

50.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Claude Sonnet 4.6; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

49%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant MiMo-V2.5-Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

48%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Agents-A1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

47.6%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5.6 Sol; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

47.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Inkling; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

46%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5.6 Terra; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

41.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5.4 mini; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

41.5%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Qwen3.7 Max; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

41.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Grok 4.5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

40.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Gemini 3.5 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

40.2%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5.3 Codex; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

39.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Gemini 3.6 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

38.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Artificial Analysis Humanity's Last Exam independent evaluation.

source label without registered configuration ID

38.3%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Gemini 3.6 Flash (Artificial Analysis) ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant DeepSeek V4 Pro (Max); bulk export does not retain a complete upstream harness configuration.

deepseek-v4-pro-max

37.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5.4 nano; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

37.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5.6 Luna; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

37.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant MiniMax M3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

37.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Claude Opus 4.6 (Adaptive); bulk export does not retain a complete upstream harness configuration.

claude-opus-4-6-max

36.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5.2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

35.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Grok 4.3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

35%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant DeepSeek V4 Flash (Max); bulk export does not retain a complete upstream harness configuration.

deepseek-v4-flash-max

34.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Kimi K2.6; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

34.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Qwen3.7 Plus; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

34.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant DeepSeek V4 Pro (High); bulk export does not retain a complete upstream harness configuration.

deepseek-v4-pro-high

34.5%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5.2-Codex; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

33.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Kimi K2.7 Code; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

32.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Hy3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

31.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Claude Opus 4.7; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

31.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Claude Opus 4.5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

30.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Kimi K2.5; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

30.1%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant DeepSeek V4 Flash (High); bulk export does not retain a complete upstream harness configuration.

deepseek-v4-flash-high

29.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Kimi K2.5 (Reasoning); bulk export does not retain a complete upstream harness configuration.

kimi-k2-5-thinking

29.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Qwen 3.6 Max (preview); bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Qwen3.6 Plus; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Qwen3.5 397B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Claude Opus 4.5 Thinking; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant MiMo-V2-Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant MiniMax M2.7; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

28.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Qwen3.5 397B (Reasoning); bulk export does not retain a complete upstream harness configuration.

qwen3-5-397b-thinking

27.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Nemotron 3 Ultra; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

26.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Gemma 4 31B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

26.5%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5.1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

26.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5 (high); bulk export does not retain a complete upstream harness configuration.

gpt-5-high

26.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Hy3 Preview; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

25.5%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GLM-5-Turbo; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

25.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GLM-4.7; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

24.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Qwen3.6-27B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

24%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Grok 4; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

23.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5 (medium); bulk export does not retain a complete upstream harness configuration.

gpt-5-medium

23.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5.1-Codex; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

23.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-5.1-Codex-Max; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

23.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Qwen3.5-122B-A10B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

23.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Qwen3.5-27B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

22.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Qwen3.6-35B-A3B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

21.4%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant o3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

20%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant MiMo-V2-Omni; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

19.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Step 3.7 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

19.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Qwen3.5-35B-A3B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

19.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Gemini 2.5 Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

18.8%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-OSS 120B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

18.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Grok 4.1 Fast (Reasoning); bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

17.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Gemini 3.5 Flash-Lite; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

17.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Artificial Analysis Humanity's Last Exam independent evaluation.

source label without registered configuration ID

17.5%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Gemini 3.5 Flash-Lite (Artificial Analysis) ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Gemma 4 26B A4B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

17.2%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Grok 4 Fast (Reasoning); bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

17%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Gemini 3.1 Flash-Lite; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

16.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GLM-5V-Turbo; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

15.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant DeepSeek-R1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

14.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Gemma 4 12B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

14.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Trinity-Large-Preview; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

14.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Trinity-Large-Thinking; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

14.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Gemini 3 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

14.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant K-Exaone; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

13.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant DeepSeek V3.1 (Reasoning); bulk export does not retain a complete upstream harness configuration.

deepseek-v3-1-reasoning-default

13%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Mistral Medium 3.5 128B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

12.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Claude 4.1 Opus Thinking; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

11.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Command A+; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

11.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Qwen3 Max; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

11.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant DeepSeek V3.2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

10.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Nemotron 3 Nano 30B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

10.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Sarvam 105B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

10.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-OSS 20B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

9.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Mistral Small 4; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

9.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Mistral Small 4 (Reasoning); bulk export does not retain a complete upstream harness configuration.

mistral-small-4-reasoning

9.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant o3-mini; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

8.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant DeepSeek V4 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

8.1%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Nemotron Ultra 253B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

8.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant DeepSeek V4 Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

7.7%

2025Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant o1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

7.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Grok Code Fast 1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

7.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Kimi K2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Sarvam 30B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant LFM2.5-8B-A1B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

6.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GLM-4.5-Air; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

6.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Granite-4.0-H-350M; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

6.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant DeepSeek V3.1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

6.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Ling 2.6 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

6.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Exaone 4.0 1.2B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Granite-4.0-350M; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant DeepSeek R1 Distill Qwen 32B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.5%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Nemotron 3 Nano Omni 30B A3B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GLM-4.6; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Gemini 2.5 Flash; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Granite-4.0-1B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant LFM2.5-VL-1.6B-Extract; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

5.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Granite-4.0-H-1B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Grok 4.1 Fast; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Exaone 4.0 32B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Gemini 1.5 Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Gemma 4 E2B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Llama 4 Maverick; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Gemma 3 27B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Gemini 1.0 Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-4.1; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-4.1 mini; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Llama 4 Scout; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Mistral Medium 3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Llama 3.1 405B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.2%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Mistral Large 3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Phi-4; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

4.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Claude 4 Sonnet; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-4o mini; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Mistral Large 2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Claude 3 Haiku; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-4.1 nano; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.9%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Qwen2.5 Coder 32B Instruct; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Solar Pro 2; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.8%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Gemma 4 E4B; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.7%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant DeepSeek V3; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.6%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Nova Pro; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.4%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-4 Turbo; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant GPT-4o; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.3%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

Exact BenchLM registry variant Claude 3 Opus; bulk export does not retain a complete upstream harness configuration.

source label without registered configuration ID

3.1%

2026Source-native system

Source carrier · no additional scoring weight

source-checked

BenchLM public datasets — 21 July 2026 ↗Observed 2026-07-21 · checked 2026-07-21

HLE-Full with tools; max reasoning; provider-published Kimi K3 evaluation.

kimi-k3-max

56%

CurrentProvider evaluation harness

Public reference · not scored

provider-reported

Kimi K3: Open Frontier Intelligence ↗Observed 2026-07-16 · checked 2026-07-21

Artificial Analysis HLE evaluation; configuration Adaptive Reasoning, Max Effort, Opus 4.8 Fallback.

claude-fable-5-max

53.3%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Humanity's Last Exam leaderboard (AA) ↗Observed 2026-07-16 · checked 2026-07-16

Artificial Analysis HLE evaluation; configuration max.

gpt-5-6-sol-max

47.2%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Humanity's Last Exam leaderboard (AA) ↗Observed 2026-07-16 · checked 2026-07-16

Artificial Analysis HLE evaluation; configuration Adaptive Reasoning, Max Effort.

claude-opus-4-8-max

45.7%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Humanity's Last Exam leaderboard (AA) ↗Observed 2026-07-16 · checked 2026-07-16

Muse Spark 1.1 (xhigh); Artificial Analysis independent evaluation configuration as published.

muse-spark-1-1-xhigh

45.1%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Humanity's Last Exam leaderboard (AA) ↗Observed 2026-07-16 · checked 2026-07-16

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

64.5%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

62.1%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

57.9%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

57.4%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

gpt-5-5-pro-default-high

57.2%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

54.7%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

53.3%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for claude-fable-5 ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

53%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

52.3%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

52.2%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

52.1%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

50.4%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

50.4%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

49%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

48%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

47.2%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for gpt-5-6-sol ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

45.7%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for claude-opus-4-8 ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

Gemini 3.1 Pro Preview

44.7%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for gemini-3-1-pro-preview ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

44.3%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for gpt-5-5 ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

41.8%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for gpt-5-6-terra ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

41.6%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for gpt-5-4 ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

41.4%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

40.3%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for grok-4-5 ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

40.2%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

39.9%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for gpt-5-3-codex ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

39.9%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for gemini-3-5-flash-medium ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

39.6%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for claude-sonnet-5 ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

38.1%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for qwen3-7-max ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

37.7%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

37.2%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for gpt-5-6-luna ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

37.1%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for minimax-m3 ↗Observed 2026-07-15 · checked 2026-07-15

Kimi K2.6

source label without registered configuration ID

35.9%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

35.9%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for deepseek-v4-pro ↗Observed 2026-07-15 · checked 2026-07-15

GPT-5.2 (xhigh)

gpt-5-2-xhigh

35.4%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

35.0%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for grok-4-3 ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

35%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

34.7%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

GPT-5.2 Codex (xhigh)

gpt-5-2-codex-xhigh

33.5%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Kimi K2.7 Code

source label without registered configuration ID

32.8%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Grok 4.20 0309 v2 (Reasoning)

source label without registered configuration ID

Grok 4.20

32.2%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

32.1%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for deepseek-v4-flash ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

30.8%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

30.1%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Qwen3.6 Max Preview

source label without registered configuration ID

Qwen3.6 Max

28.9%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

28.8%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Qwen3.5 397B A17B (Reasoning)

source label without registered configuration ID

27.3%

CurrentArtificial Analysis independent evaluation

Score input

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

GPT-5.4 mini (xhigh)

gpt-5-4-mini-xhigh

26.6%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Nemotron 3 Ultra 550B A55B (Reasoning)

source label without registered configuration ID

26.6%

CurrentArtificial Analysis independent evaluation

Score input

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

GPT-5 (high)

gpt-5-high

26.5%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

26.5%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Qwen3 Max Thinking

source label without registered configuration ID

26.2%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

GPT-5 Codex (high)

gpt-5-codex-high

GPT-5 Codex

25.6%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

MiMo-V2.5

source label without registered configuration ID

MiMo-V2.5

25.2%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

GLM-4.7 (Reasoning)

source label without registered configuration ID

25.1%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Grok 4

source label without registered configuration ID

23.9%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Qwen3.5 122B A10B (Reasoning)

source label without registered configuration ID

Qwen3.5 122B

23.4%

CurrentArtificial Analysis independent evaluation

Score input

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Kimi K2 Thinking

source label without registered configuration ID

Kimi K2 Thinking

22.3%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

DeepSeek V3.2 (Reasoning)

source label without registered configuration ID

22.2%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Qwen3.5 27B (Reasoning)

source label without registered configuration ID

22.2%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

MiniMax-M2.1

source label without registered configuration ID

MiniMax M2.1

22.2%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Qwen3.6 27B (Reasoning)

source label without registered configuration ID

21.6%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Gemini 2.5 Pro

source label without registered configuration ID

21.1%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

source label without registered configuration ID

20.0%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Qwen3.5 35B A3B (Reasoning)

source label without registered configuration ID

Qwen3.5 35B

19.7%

CurrentArtificial Analysis independent evaluation

Score input

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

NVIDIA Nemotron 3 Super 120B A12B (Reasoning)

source label without registered configuration ID

Nemotron 3 Super

19.2%

CurrentArtificial Analysis independent evaluation

Score input

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

MiniMax-M2.5

source label without registered configuration ID

MiniMax M2.5

19.1%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Gemma 4 26B A4B (Reasoning)

source label without registered configuration ID

Gemma 4 26B

18.3%

CurrentArtificial Analysis independent evaluation

Score input

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

o4-mini (high)

o4-mini-high

o4-mini

17.5%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Claude 4.5 Sonnet (Reasoning)

source label without registered configuration ID

Claude Sonnet 4.5

17.3%

CurrentArtificial Analysis independent evaluation

Score input

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Grok 4 Fast (Reasoning)

source label without registered configuration ID

Grok 4 Fast

17.0%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

DeepSeek V3.1 Terminus (Reasoning)

source label without registered configuration ID

DeepSeek V3.1 Terminus

15.2%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Gemma 4 12B (Reasoning)

source label without registered configuration ID

14.8%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

GPT-5 mini (medium)

gpt-5-mini-medium

GPT-5 mini

14.6%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Qwen3.5 Omni Plus

source label without registered configuration ID

Qwen3.5 Omni Plus

13.9%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

GLM-4.6 (Reasoning)

source label without registered configuration ID

13.3%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

Mistral Medium 3.5

12.8%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for mistral-medium-3-5 ↗Observed 2026-07-15 · checked 2026-07-15

Gemini 2.5 Flash Preview (Sep '25) (Reasoning)

source label without registered configuration ID

12.7%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

MiniMax-M2

source label without registered configuration ID

MiniMax M2

12.5%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Claude 4.1 Opus (Reasoning)

source label without registered configuration ID

Claude Opus 4.1

11.9%

CurrentArtificial Analysis independent evaluation

Score input

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Claude 4 Opus (Reasoning)

source label without registered configuration ID

Claude Opus 4

11.7%

CurrentArtificial Analysis independent evaluation

Score input

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Command A+

source label without registered configuration ID

11.4%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Grok 3 mini Reasoning (high)

source label without registered configuration ID

Grok 3 mini

11.1%

CurrentArtificial Analysis independent evaluation

Score input

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Claude 3.7 Sonnet (Reasoning)

source label without registered configuration ID

Claude Sonnet 3.7

10.3%

CurrentArtificial Analysis independent evaluation

Score input

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Claude 4 Sonnet (Reasoning)

source label without registered configuration ID

Claude Sonnet 4

9.6%

CurrentArtificial Analysis independent evaluation

Score input

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

9.5%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for mistral-small-4 ↗Observed 2026-07-15 · checked 2026-07-15

Nova 2.0 Pro Preview (medium)

source label without registered configuration ID

Nova 2 Pro

8.9%

CurrentArtificial Analysis independent evaluation

Score input

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Ling-2.6-1T

source label without registered configuration ID

Ling 2.6 1T

8.2%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

8.1%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

source label without registered configuration ID

7.7%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Exact model variant as listed on the BenchLM public benchmark leaderboard page.

source label without registered configuration ID

7.7%

CurrentBenchLM aggregated public evaluation

Source carrier · no additional scoring weight

source-checked

BenchLM public benchmark leaderboards ↗Observed 2026-07-15 · checked 2026-07-15

Grok Code Fast 1

source label without registered configuration ID

7.5%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Kimi K2 0905

source label without registered configuration ID

Kimi K2 0905

6.3%

CurrentArtificial Analysis independent evaluation

Public reference · not scored

source-checked

Artificial Analysis Models Leaderboard ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

Claude Haiku 4.5

4.3%

CurrentArtificial Analysis evaluation harness

Score input

source-checked

Artificial Analysis evaluations for claude-4-5-haiku ↗Observed 2026-07-15 · checked 2026-07-15

Artificial Analysis public model evaluation page; exact provider variant as listed on the page.

source label without registered configuration ID

4.1%

CurrentArtificial Analysis evaluation harness

Public reference · not scored

source-checked

Artificial Analysis evaluations for mistral-large-3 ↗Observed 2026-07-15 · checked 2026-07-15

Muse Spark 1.1; provider evaluation configuration as published in the Meta Muse Spark 1.1 evaluation report (Humanity's Last Exam (with tools as published)).

muse-spark-1-1-xhigh

62.1%

CurrentProvider evaluation harness

Public reference · not scored

provider-reported

Meta AI Muse Spark 1.1 evaluation report ↗Observed 2026-07-09 · checked 2026-07-16

tencent/Hy3 instruct weights; configuration as recorded on the Hugging Face evaluation results entry.

source label without registered configuration ID

53.2%

CurrentProvider / community evaluation result attached on Hugging Face

Score input

provider-reported

Tencent Hy3 model card on Hugging Face ↗Observed 2026-07-06 · checked 2026-07-16

Exact model variant and provider evaluation configuration stated in the Gemini 3.5 Flash model card; single-attempt where specified.

source label without registered configuration ID

Gemini 3.1 Pro Preview

44.4%

CurrentProvider evaluation harness

Public reference · not scored

provider-reported

Gemini 3.5 Flash model card ↗Observed 2026-05-19 · checked 2026-07-15

Exact model variant and provider evaluation configuration stated in the Gemini 3.5 Flash model card; single-attempt where specified.

source label without registered configuration ID

41.4%

CurrentProvider evaluation harness

Public reference · not scored

provider-reported

Gemini 3.5 Flash model card ↗Observed 2026-05-19 · checked 2026-07-15

Exact model variant and provider evaluation configuration stated in the Gemini 3.5 Flash model card; single-attempt where specified.

source label without registered configuration ID