math benchmark
MMVet
MM-Vet is an evaluation benchmark that examines large multimodal models on complicated multimodal tasks requiring integrated capabilities. It assesses six core vision-language capabilities: recognition, knowledge, spatial awareness, language generation, OCR, and math through questions that require one or more of these capabilities.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
MMVet leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 76.2% | 100.0% | 2 | C | |
| 2 | AC | 67.1% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
MMVet highlights
The top published results on this benchmark's own scale.
What is MMVet?
Definition and scoring fields from the benchmark registry.
MM-Vet is an evaluation benchmark that examines large multimodal models on complicated multimodal tasks requiring integrated capabilities. It assesses six core vision-language capabilities: recognition, knowledge, spatial awareness, language generation, OCR, and math through questions that require one or more of these capabilities.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MMVet
- Modality
- multimodal
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mmvet|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MMVet.
Which model scores highest on MMVet?
Qwen2.5 VL 72B Instruct is currently ranked first with 76.2%.
What does MMVet measure?
MM-Vet is an evaluation benchmark that examines large multimodal models on complicated multimodal tasks requiring integrated capabilities. It assesses six core vision-language capabilities: recognition, knowledge, spatial awareness, language generation, OCR, and math through questions that require one or more of these capabilities.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.