multimodal benchmark
MMStar
MMStar is an elite vision-indispensable multimodal benchmark comprising 1,500 challenge samples meticulously selected by humans to evaluate 6 core capabilities and 18 detailed axes. The benchmark addresses issues of visual content unnecessity and unintentional data leakage in existing multimodal evaluations.
Updated Aug 11, 2026
Models22
Model coverage22
MetricScore
EvidenceB
MMStar Ranking
Higher score ranks better on this benchmark.
MMStar Score Distribution
A closer view of the leading scores on this benchmark.
MMStar Highlights
The leading models and scores on this benchmark.
What is MMStar?
What MMStar measures and how its scores work.
MMStar is an elite vision-indispensable multimodal benchmark comprising 1,500 challenge samples meticulously selected by humans to evaluate 6 core capabilities and 18 detailed axes. The benchmark addresses issues of visual content unnecessity and unintentional data leakage in existing multimodal evaluations.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MMStar
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- mmstar|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MMStar.
Which model scores highest on MMStar?
Qwen3.6 Plus is currently ranked first with 83.3%.
What does MMStar measure?
MMStar is an elite vision-indispensable multimodal benchmark comprising 1,500 challenge samples meticulously selected by humans to evaluate 6 core capabilities and 18 detailed axes. The benchmark addresses issues of visual content unnecessity and unintentional data leakage in existing multimodal evaluations.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
22 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.