multimodal benchmark
MMBench
A bilingual benchmark for assessing multi-modal capabilities of vision-language models through multiple-choice questions in both English and Chinese, providing systematic evaluation across diverse vision-language tasks with robust metrics.
Updated Aug 11, 2026
Models9
Model coverage9
MetricScore
EvidenceB
MMBench Ranking
Higher score ranks better on this benchmark.
| 01 | ST | 91.8% | 100.0% | 9 | C | |
| 02 | AC | 88.0% | 87.5% | 9 | C | |
| 03 | MI | 86.7% | 75.0% | 9 | C | |
| 04 | AC | 86.5% | 62.5% | 9 | C | |
| 05 | AC | 84.3% | 50.0% | 9 | C | |
| 06 | MI | 81.9% | 37.5% | 9 | C | |
| 07 | DE | 80.3% | 25.0% | 9 | C | |
| 08 | DE | 79.6% | 12.5% | 9 | C | |
| 09 | DE | 69.2% | 0.0% | 9 | C |
MMBench Score Distribution
A closer view of the leading scores on this benchmark.
MMBench Highlights
The leading models and scores on this benchmark.
What is MMBench?
What MMBench measures and how its scores work.
A bilingual benchmark for assessing multi-modal capabilities of vision-language models through multiple-choice questions in both English and Chinese, providing systematic evaluation across diverse vision-language tasks with robust metrics.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MMBench
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- mmbench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MMBench.
Which model scores highest on MMBench?
Step3-VL-10B is currently ranked first with 91.8%.
What does MMBench measure?
A bilingual benchmark for assessing multi-modal capabilities of vision-language models through multiple-choice questions in both English and Chinese, providing systematic evaluation across diverse vision-language tasks with robust metrics.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
9 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.