Skip to content

Benchmark

MLVU-M

Scores are percentages.

Models measured
5
Scores recorded
6
Sources
1
IQ weight
0.27

Score distribution

78.4%
Mean
78.9%
Median
2.8%
Std dev
75.1%
10th percentile
82.1%
90th percentile
74.6%
Min
74.6%82.1%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.27 for chat models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.82.1%
2qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.81.3%
3qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.78.9%
4Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.78.1%
5Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.75.1%
6Qwen2.5 VL 72B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.6%

Data credits: Data by LLM Stats