Our data / Models
Models
Benchmark results and API pricing, by model.
Anthropic
27- AnthropicClaude Fable 5.17 benchmarks
- AnthropicClaude Fable 56 benchmarks
- AnthropicClaude Opus 5.511 benchmarks
- AnthropicClaude Opus 59 benchmarks
- AnthropicClaude Opus 4.87 benchmarks
- AnthropicClaude Opus 4.71 benchmark
- AnthropicClaude Opus 4.65 benchmarks
- AnthropicClaude Opus 4.54 benchmarks
- AnthropicClaude Opus 4 1 202508053 benchmarks
- AnthropicClaude Opus 43 benchmarks
- AnthropicClaude 3 Opus 202402292 benchmarks
- AnthropicClaude Sonnet 5.512 benchmarks
- AnthropicClaude Sonnet 56 benchmarks
- AnthropicClaude Sonnet 4.64 benchmarks
- AnthropicClaude Sonnet 4.54 benchmarks
- AnthropicClaude Sonnet 43 benchmarks
- AnthropicClaude 3 Sonnet 202402292 benchmarks
- AnthropicClaude 3 5 Sonnet 202410222 benchmarks
- AnthropicClaude 3 5 Sonnet 202406202 benchmarks
- AnthropicClaude Haiku 5.510 benchmarks
- AnthropicClaude Haiku 4.53 benchmarks
- AnthropicClaude 3 Haiku 202403072 benchmarks
- AnthropicClaude 3 5 Haiku 202410222 benchmarks
- AnthropicClaude 4.74 benchmarks
- AnthropicClaude 3.73 benchmarks
- AnthropicClaude 2.12 benchmarks
- AnthropicClaude 2.02 benchmarks
OpenAI
55- OpenAIGPT-6 Astra11 benchmarks
- OpenAIGPT-6.1 Sol10 benchmarks
- OpenAIGPT-6 Sol8 benchmarks
- OpenAIGPT-5.6 Sol9 benchmarks
- OpenAIGPT-6.1 Terra7 benchmarks
- OpenAIGPT-5.6 Terra8 benchmarks
- OpenAIGPT-6 Luna7 benchmarks
- OpenAIGPT-5.6 Luna 2026-07-302 benchmarks
- OpenAIGPT-5.6 Luna8 benchmarks
- OpenAIo4-mini4 benchmarks
- OpenAIo3-mini4 benchmarks
- OpenAIo34 benchmarks
- OpenAIo1-mini3 benchmarks
- OpenAIo1 Preview 2024 09 122 benchmarks
- OpenAIo1 2024 12 172 benchmarks
- OpenAIGPT-Oss 120b3 benchmarks
- OpenAIGPT-Oss 20b2 benchmarks
- OpenAIGPT-5.5 Pro Pre Release2 benchmarks
- OpenAIGPT-5.5 Pro2 benchmarks
- OpenAIGPT-5.5 Pre Release2 benchmarks
- OpenAIGPT-5.5 Instant2 benchmarks
- OpenAIGPT-5.55 benchmarks
- OpenAIGPT-5.4 Pro3 benchmarks
- OpenAIGPT-5.4 Nano4 benchmarks
- OpenAIGPT-5.4 Mini4 benchmarks
- OpenAIGPT-5.45 benchmarks
- OpenAIGPT-5.2 Pro2 benchmarks
- OpenAIGPT-5.24 benchmarks
- OpenAIGPT-5.14 benchmarks
- OpenAIGPT-5 Pro2 benchmarks
- OpenAIGPT-5 Nano4 benchmarks
- OpenAIGPT-5 Mini4 benchmarks
- OpenAIGPT-54 benchmarks
- OpenAIGPT-4o-mini3 benchmarks
- OpenAIGPT-4o Mini 2024 07 181 benchmark
- OpenAIGPT-4o 2024 11 201 benchmark
- OpenAIGPT-4o 2024 08 062 benchmarks
- OpenAIGPT-4o 2024 05 132 benchmarks
- OpenAIGPT-4o2 benchmarks
- OpenAIGPT-4.5 Preview 2025 02 272 benchmarks
- OpenAIGPT-4.52 benchmarks
- OpenAIGPT-4.1-Nano2 benchmarks
- OpenAIGPT-4.1-Mini3 benchmarks
- OpenAIGPT-4.1 Nano 2025 04 141 benchmark
- OpenAIGPT-4.1 Mini 2025 04 141 benchmark
- OpenAIGPT-4.1 2025 04 141 benchmark
- OpenAIGPT-4.12 benchmarks
- OpenAIGPT-4 Turbo 2024 04 092 benchmarks
- OpenAIGPT-4 1106 Preview2 benchmarks
- OpenAIGPT-4 06133 benchmarks
- OpenAIGPT-4 03142 benchmarks
- OpenAIGPT-4 0125 Preview2 benchmarks
- OpenAIGPT-3.5 Turbo 11062 benchmarks
- OpenAIGPT-3.5 Turbo 01253 benchmarks
- OpenAICodex Mini (Latest)2 benchmarks
- GoogleGemini 4 Argon11 benchmarks
- GoogleGemini 3.8 Flash12 benchmarks
- GoogleGemini 3.7 Flash5 benchmarks
- GoogleGemini 3.6 Flash4 benchmarks
- GoogleGemini 3.5 Flash-Lite4 benchmarks
- GoogleGemini 3.5 Flash4 benchmarks
- GoogleGemini 3.1 Flash Lite2 benchmarks
- GoogleGemini 3 Flash Preview4 benchmarks
- GoogleGemini 2.5 Flash (Preview)2 benchmarks
- GoogleGemini 2.0 Flash2 benchmarks
- GoogleGemini 1.5 Flash 8b 0012 benchmarks
- GoogleGemini 1.5 Flash 0022 benchmarks
- GoogleGemini 1.5 Flash 0012 benchmarks
- GoogleGemma 4 31b It2 benchmarks
- GoogleGemma 4 26b a4b It2 benchmarks
- GoogleGemma 3 27b It2 benchmarks
- GoogleGemma 3 12b It2 benchmarks
- GoogleGemma 3 4b It2 benchmarks
- GoogleGemma 3 1b It2 benchmarks
- GoogleGemma 2 27b It2 benchmarks
- GoogleGemma 2 9b It2 benchmarks
- GoogleGemini 3.1 Pro (Preview)5 benchmarks
- GoogleGemini 3 Pro Preview1 benchmark
- GoogleGemini 3 Pro2 benchmarks
- GoogleGemini 3 Deep Think (2/26)2 benchmarks
- GoogleGemini 2.5 Pro Preview 06 052 benchmarks
- GoogleGemini 2.5 Pro Preview 05 062 benchmarks
- GoogleGemini 2.5 Pro Exp 03 252 benchmarks
- GoogleGemini 2.5 Pro3 benchmarks
- GoogleGemini 2.0 Pro Exp 02 052 benchmarks
- GoogleGemini 1.5 Pro 0022 benchmarks
- GoogleGemini 1.5 Pro 0012 benchmarks
- GoogleGemini 1.5 Pro2 benchmarks
- GoogleGemini 1.0 Pro 0012 benchmarks
xAI
11- xAIGrok 4.20 (Reasoning)3 benchmarks
- xAIGrok 4.20 (Beta Reasoning)1 benchmark
- xAIGrok 4.712 benchmarks
- xAIGrok 4.67 benchmarks
- xAIGrok 4.55 benchmarks
- xAIGrok 4.32 benchmarks
- xAIGrok 4 (Fast Reasoning)2 benchmarks
- xAIGrok 43 benchmarks
- xAIGrok 3 Mini3 benchmarks
- xAIGrok 33 benchmarks
- xAIGrok 2 12122 benchmarks
Meta
15- MetaMuse Wonder5 benchmarks
- MetaMuse Spark Open5 benchmarks
- MetaMuse Spark 1.36 benchmarks
- MetaMuse Spark2 benchmarks
- MetaMeta Llama 3 70B Instruct2 benchmarks
- MetaMeta Llama 3 8B Instruct2 benchmarks
- MetaLlama 4 Scout3 benchmarks
- MetaLlama 4 Maverick3 benchmarks
- MetaLlama 3.3 70B Instruct2 benchmarks
- MetaLlama 3.2 90B Vision Instruct2 benchmarks
- MetaLlama 3.2 1B Instruct2 benchmarks
- MetaLlama 3.1 405B Instruct2 benchmarks
- MetaLlama 3.1 70B Instruct2 benchmarks
- MetaLlama 3.1 8B Instruct2 benchmarks
- MetaLlama 2 70b Chat Hf2 benchmarks
DeepSeek
17- DeepSeekDeepSeek V4.1 Flash 10177 benchmarks
- DeepSeekDeepSeek V4.1 Flash5 benchmarks
- DeepSeekDeepSeek V4 Pro 08134 benchmarks
- DeepSeekDeepSeek V4 Pro4 benchmarks
- DeepSeekDeepSeek V4 Flash 07314 benchmarks
- DeepSeekDeepseek V3.22 benchmarks
- DeepSeekDeepSeek V3 03242 benchmarks
- DeepSeekDeepSeek V32 benchmarks
- DeepSeekDeepSeek Reasoner2 benchmarks
- DeepSeekDeepSeek R1 Distill Qwen 32B2 benchmarks
- DeepSeekDeepSeek R1 Distill Qwen 14B2 benchmarks
- DeepSeekDeepSeek R1 Distill Qwen 1.5B2 benchmarks
- DeepSeekDeepSeek R1 Distill Llama 70B2 benchmarks
- DeepSeekDeepseek R1 (05/28)3 benchmarks
- DeepSeekDeepseek R13 benchmarks
- DeepSeekDeepSeek Llm 67b Chat2 benchmarks
- DeepSeekDeepSeek Chat2 benchmarks
Z.ai
4
Alibaba
41- AlibabaQwQ Plus2 benchmarks
- AlibabaQwQ 32B2 benchmarks
- AlibabaQwen3.8-27B2 benchmarks
- Alibabaqwen3.8 Max 09022 benchmarks
- Alibabaqwen3.8 Max3 benchmarks
- Alibabaqwen3.7 Plus3 benchmarks
- Alibabaqwen3.7 Max3 benchmarks
- Alibabaqwen3.7 Flash3 benchmarks
- Alibabaqwen3.6 Plus3 benchmarks
- Alibabaqwen3.6 Max Preview3 benchmarks
- Alibabaqwen3.6 Flash3 benchmarks
- Alibabaqwen3.6 35b a3b3 benchmarks
- Alibabaqwen3.6 27b3 benchmarks
- AlibabaQwen3.5-122B-A10B2 benchmarks
- Alibabaqwen3.5 Plus3 benchmarks
- Alibabaqwen3.5 Flash3 benchmarks
- Alibabaqwen3.5 397b a17b3 benchmarks
- Alibabaqwen3.5 35b a3b2 benchmarks
- Alibabaqwen3.5 9B2 benchmarks
- AlibabaQwen3-235b-a22b Instruct (25/07)2 benchmarks
- Alibabaqwen3 Max 2025 09 233 benchmarks
- AlibabaQwen3 235B A22B Thinking 25073 benchmarks
- Alibabaqwen3 235b a22b2 benchmarks
- AlibabaQwen3 32B2 benchmarks
- Alibabaqwen3 30b a3b Thinking 25072 benchmarks
- Alibabaqwen3 30b a3b Instruct 25072 benchmarks
- AlibabaQwen3 30B A3B2 benchmarks
- Alibabaqwen3 14b2 benchmarks
- Alibabaqwen3 8b2 benchmarks
- Alibabaqwen3 4b2 benchmarks
- Alibabaqwen3 1.7b2 benchmarks
- Alibabaqwen2.5 72b Instruct2 benchmarks
- Alibabaqwen2.5 32b Instruct2 benchmarks
- Alibabaqwen2.5 7b Instruct2 benchmarks
- Alibabaqwen2 72b Instruct2 benchmarks
- Alibabaqwen1.5 72b Chat2 benchmarks
- Alibabaqwen1.5 32b Chat2 benchmarks
- AlibabaQwen Turbo 2024 11 012 benchmarks
- AlibabaQwen Plus 2025 01 252 benchmarks
- AlibabaQwen Max 2025 01 252 benchmarks
- AlibabaQwen 3.8 Max 09022 benchmarks
Cursor
1
01.AI
2Allen Institute for AI,University of Washington
1Databricks
1Dots Studio
1Google DeepMind,Google
2Microsoft
2Microsoft Research
1MiniMax
2Mistral
22- MistralOpen Mixtral 8x22b2 benchmarks
- MistralOpen Mixtral 8x7b2 benchmarks
- MistralOpen Mistral Nemo 24072 benchmarks
- MistralOpen Mistral 7b2 benchmarks
- MistralMixtral 8x7B Instruct v0.12 benchmarks
- MistralMistral Small 25032 benchmarks
- MistralMistral Small 25012 benchmarks
- MistralMistral Small 3.2 25062 benchmarks
- MistralMistral Small 3.1 25032 benchmarks
- MistralMistral Small 3 25012 benchmarks
- MistralMistral Medium 25052 benchmarks
- MistralMistral Large 24112 benchmarks
- MistralMistral Large 24072 benchmarks
- MistralMistral Large 24022 benchmarks
- MistralMistral Large 4 03 benchmarks
- MistralMistral 7B Instruct v0.32 benchmarks
- MistralMinistral 8b 24102 benchmarks
- MistralMinistral 3b 24102 benchmarks
- MistralMagistral Small 25092 benchmarks
- MistralMagistral Small 25061 benchmark
- MistralMagistral Small2 benchmarks
- MistralMagistral Medium2 benchmarks
Moonshot
4Moonshot AI
2Not specified
7- Not specifiedSeed Oss 36b Instruct2 benchmarks
- Not specifiedqwen3 4b Instruct 25072 benchmarks
- Not specifiedGranite 4.0 Micro2 benchmarks
- Not specifiedGranite 4.0 350m2 benchmarks
- Not specifiedGranite 4.0 1b2 benchmarks
- Not specifiedGLM 4.7 Flash2 benchmarks
- Not specifiedDeepSeek r1 0528 qwen3 8b2 benchmarks