general benchmark
MLVU-M Leaderboard
MLVU-M is a general benchmark with a Score reported as a ratio.
Updated Sep 5, 2026
Models8
Model coverage8
MetricScore
EvidenceB
MLVU-M Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score82.10% | Percentile100.00% | Participants8 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score81.30% | Percentile85.71% | Participants8 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score78.90% | Percentile71.43% | Participants8 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score78.10% | Percentile57.14% | Participants8 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score75.70% | Percentile42.86% | Participants8 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score75.30% | Percentile28.57% | Participants8 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score75.10% | Percentile14.29% | Participants8 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score74.60% | Percentile0.00% | Participants8 | EvidenceC | Evaluated |
MLVU-M Highlights
The leading models and scores on this benchmark.
MLVU-M Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MLVU-M
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MLVU-M?
What MLVU-M measures and how its scores work.
MLVU-M is a benchmark.
It reports a Score as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MLVU-M
- Modality
- text
- Primary category
- general
- 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 MLVU-M.
Which model scores highest on MLVU-M?
Qwen3 VL 32B Instruct is currently ranked first with 82.10%.
What are the top three models on MLVU-M?
The current leaders are Qwen3 VL 32B Instruct (82.10%), Qwen3 VL 30B A3B Instruct (81.30%), and Qwen3 VL 30B A3B Thinking (78.90%).
Which MLVU-M model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among MLVU-M results?
The fastest matched records are Qwen3 VL 4B Thinking (8.77 tok/s via DeepInfra).
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.