multimodal benchmark
MMStar Leaderboard
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 17, 2026
Models24
Model coverage24
MetricScore
EvidenceB
MMStar Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score83.3% | Percentile100.0% | Participants24 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score82.9% | Percentile95.7% | Participants24 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score81.9% | Percentile91.3% | Participants24 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score81.4% | Percentile87.0% | Participants24 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score81.0% | Percentile82.6% | Participants24 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score79.4% | Percentile78.3% | Participants24 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score78.7% | Percentile73.9% | Participants24 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score78.4% | Percentile69.6% | Participants24 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score77.7% | Percentile65.2% | Participants24 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score75.5% | Percentile60.9% | Participants24 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score75.3% | Percentile56.5% | Participants24 | EvidenceC | Evaluated |
| Rank12 | ModelAC | Score73.2% | Percentile52.2% | Participants24 | EvidenceC | Evaluated |
| Rank13 | ModelAC | Score72.1% | Percentile47.8% | Participants24 | EvidenceC | Evaluated |
| Rank14 | ModelAC | Score70.9% | Percentile43.5% | Participants24 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score70.8% | Percentile39.1% | Participants24 | EvidenceC | Evaluated |
| Rank16 | ModelAC | Score69.8% | Percentile34.8% | Participants24 | EvidenceC | Evaluated |
| Rank17 | ModelAC | Score69.5% | Percentile30.4% | Participants24 | EvidenceC | Evaluated |
| Rank18 | ModelAC | Score64.0% | Percentile26.1% | Participants24 | EvidenceC | Evaluated |
| Rank19 | ModelAC | Score63.9% | Percentile21.7% | Participants24 | EvidenceC | Evaluated |
| Rank20 | ModelLA | Score63.3% | Percentile17.4% | Participants24 | EvidenceC | Evaluated |
| Rank21 | ModelDE | Score61.3% | Percentile13.0% | Participants24 | EvidenceC | Evaluated |
| Rank22 | ModelDE | Score57.0% | Percentile8.7% | Participants24 | EvidenceC | Evaluated |
| Rank23 | ModelCO | Score51.8% | Percentile4.3% | Participants24 | EvidenceC | Evaluated |
| Rank24 | ModelDE | Score45.9% | Percentile0.0% | Participants24 | EvidenceC | Evaluated |
MMStar Highlights
The leading models and scores on this benchmark.
MMStar Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MMStar
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis mmstar AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ACQwen3.6 PlusAlibaba Cloud / Qwen Team
- Score
- 83.3%
- Price
- $0.50 input / $3.0 output per 1M tokens
- Speed
- Up to 16 tok/s via Together
Strengths
- Ranks #1 of 24 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures MMStar, not total model capability
- 02ACQwen3.5-122B-A10BAlibaba Cloud / Qwen Team
- Score
- 82.9%
- Price
- $0.40 input / $3.2 output per 1M tokens
Strengths
- Ranks #2 of 24 compared models
- 96th percentile on this benchmark
- C evidence result
Considerations
- This result measures MMStar, not total model capability
- 03ACQwen3.5-35B-A3BAlibaba Cloud / Qwen Team
- Score
- 81.9%
- Price
- $0.25 input / $2.0 output per 1M tokens
Strengths
- Ranks #3 of 24 compared models
- 91th percentile on this benchmark
- C evidence result
Considerations
- This result measures MMStar, not total model capability
- 04ACQwen3.6-27BAlibaba Cloud / Qwen Team
- Score
- 81.4%
- Price
- $0.60 input / $3.6 output per 1M tokens
- Speed
- Up to 6.1 tok/s via Novita
Strengths
- Ranks #4 of 24 compared models
- 87th percentile on this benchmark
- C evidence result
Considerations
- This result measures MMStar, not total model capability
- 05ACQwen3.5-27BAlibaba Cloud / Qwen Team
- Score
- 81.0%
- Price
- $0.30 input / $2.4 output per 1M tokens
- Speed
- Up to 6.7 tok/s via Novita
Strengths
- Ranks #5 of 24 compared models
- 83th percentile on this benchmark
- C evidence result
Considerations
- This result measures MMStar, not total model capability
Selection summary
Best AI Models for MMStar
Qwen3.6 Plus currently leads MMStar with 83.3%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
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?
24 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.