Multimodal · Benchmark profile

Massive Multi-discipline Multimodal Understanding

A broad multimodal reasoning benchmark spanning charts, diagrams, tables, and academic visual question answering.

Reference2024Active9 models

Data verified 27 Jul 2026 · Methodology 1.8.0

Benchmark score on Massive Multi-discipline Multimodal Understanding

Leaderboard · 9 models

Qwen3.6 Plus leads at 86%, followed by Qwen3.5-122B-A10B (83.9%) and Qwen3.6 27B (82.9%).

Display onlyMultimodal2024

#1Closed

Qwen3.6 Plus

Alibaba Cloud

qwen3-6-plus

86%

Overall #29 · Context 1M tokens

#2Open

Qwen3.5-122B-A10B

Alibaba Cloud

qwen3-5-122b-a10b

83.9%

Overall — · Context 262K tokens

#3Open

Qwen3.6 27B

Alibaba Cloud

qwen3.6-27b

82.9%

Overall #59 · Context 262K tokens

View

ModelsColours

Alibaba CloudCohereNVIDIALiquidAI

Lumina

Massive Multi-discipline Multimodal Understanding leaderboard

9 ranked models · higher is better · labels show rank and score

View accessible chart data

Accessible data for Massive Multi-discipline Multimodal Understanding leaderboard
Model	Rank	Provider	Score
Qwen3.6 Plus	#1	Alibaba Cloud	86%
Qwen3.5-122B-A10B	#2	Alibaba Cloud	83.9%
Qwen3.6 27B	#3	Alibaba Cloud	82.9%
Qwen3.5 27B	#4	Alibaba Cloud	82.3%
Qwen3.6-35B-A3B	#5	Alibaba Cloud	81.7%
Qwen3.5-35B-A3B	#6	Alibaba Cloud	81.4%
Command A+	#7	Cohere	75.1%
Nemotron 3 Nano Omni 30B A3B	#8	NVIDIA	70.8%
LFM2.5-VL-450M	#9	LiquidAI	32.7%

Benchmark score table (9 models)

One best score per model · higher is better

Massive Multi-discipline Multimodal Understanding leaderboard ranked by score
Rank	Model	Provider	License	Evidence use	Score
#1	Qwen3.6 Plus qwen3-6-plus	Alibaba Cloud	closed	Reference only	86%
#2	Qwen3.5-122B-A10B qwen3-5-122b-a10b	Alibaba Cloud	open	Reference only	83.9%
#3	Qwen3.6 27B qwen3.6-27b	Alibaba Cloud	open	Estimated reference	82.9%
#4	Qwen3.5 27B qwen3.5-27b	Alibaba Cloud	open	Reference only	82.3%
#5	Qwen3.6-35B-A3B qwen3-6-35b-a3b	Alibaba Cloud	open	Estimated reference	81.7%
#6	Qwen3.5-35B-A3B qwen3-5-35b-a3b	Alibaba Cloud	open	Reference only	81.4%
#7	Command A+ command-a-plus	Cohere	open	Estimated reference	75.1%
#8	Nemotron 3 Nano Omni 30B A3B nemotron-3-nano-omni-30b-a3b	NVIDIA	open	Estimated reference	70.8%
#9	LFM2.5-VL-450M lfm2-5-vl-450m	LiquidAI	open	Estimated reference	32.7%

The top of this snapshot is led by Qwen3.6 Plus at 86%; third place is 3.1 points behind. The top-9 spread is 53.3 points.

Compare top models

Qwen3.6 Plus vs Qwen3.5-122B-A10B Qwen3.5-122B-A10B vs Qwen3.6 27B Qwen3.6 27B vs Qwen3.5 27B Qwen3.5 27B vs Qwen3.6-35B-A3B

About Massive Multi-discipline Multimodal Understanding

Definition and scoring

Organisation: MMMU authors
Category: Multimodal
Version: 2024
Direction: higher is better
Ranking use: Reference
Contamination risk: Unknown

A broad multimodal reasoning benchmark spanning charts, diagrams, tables, and academic visual question answering. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.

Open benchmark source ↗

FAQ

Quick answers

What does Massive Multi-discipline Multimodal Understanding measure?

A broad multimodal reasoning benchmark spanning charts, diagrams, tables, and academic visual question answering.

Which model scores highest on Massive Multi-discipline Multimodal Understanding?

Qwen3.6 Plus by Alibaba Cloud currently leads with 86%.

How many models are evaluated on Massive Multi-discipline Multimodal Understanding?

9 models in the LuminaBench cohort have a qualifying score on this benchmark.

Does this affect overall Lumina rank?

No. This benchmark is display-only and does not enter the overall Lumina composite.

MMMU

Rolling · 1 results · Not Weighted

MMMU-Pro

Rolling · 238 results · Weighted 4.2%

MathVista

Rolling · Not evaluated · Not Weighted

ChartQA

Rolling · Not evaluated · Not Weighted

DocVQA

Rolling · Not evaluated · Not Weighted

CharXiv

May 2026 · 82 results · Weighted 4.2%

Multimodal · Benchmark profile

Massive Multi-discipline Multimodal Understanding

A broad multimodal reasoning benchmark spanning charts, diagrams, tables, and academic visual question answering.

Reference2024Active9 models

Data verified 27 Jul 2026 · Methodology 1.8.0

Benchmark score on Massive Multi-discipline Multimodal Understanding