Skip to content

Benchmark

MMMU-Pro (with tools)

Vision benchmarks measure how well models understand images. Scores are percentages.

Models measured
5
Scores recorded
5
Sources
1
IQ weight
0.88

Score distribution

83.9%
Mean
83.4%
Median
3.5%
Std dev
79.5%
10th percentile
90%
90th percentile
79.5%
Min
79.5%90%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.88 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
1Kimi K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90%
2GPT-5.6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim84.6%
3Kimi K3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.4%
4GPT-5.6 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82%
5GPT-5.6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79.5%

Data credits: Data by LLM Stats