math benchmark
MMVet Leaderboard
MMVet evaluates large multimodal models on complicated multimodal tasks requiring integrated capabilities.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
MMVet Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score76.19% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score67.10% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
MMVet Highlights
The leading models and scores on this benchmark.
MMVet Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MMVet
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MMVet?
What MMVet measures and how its scores work.
MMVet is an evaluation benchmark for large multimodal models.
It measures recognition, knowledge, spatial awareness, language generation, OCR, and math through questions requiring one or more of these capabilities.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MMVet
- Modality
- multimodal
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MMVet.
Which model scores highest on MMVet?
Qwen2.5 VL 72B Instruct is currently ranked first with 76.19%.
What are the top three models on MMVet?
The current leaders are Qwen2.5 VL 72B Instruct (76.19%) and Qwen2.5 VL 7B Instruct (67.10%).
Which MMVet model has the lowest official input price?
Qwen2.5 VL 7B Instruct has the lowest matched official input price at $0.35 input / $1.1 output per 1M tokens.
Which models are fastest among MMVet results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.