Skip to content

Benchmark

MMMU - Health & Medicine

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

Models measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

52.6%
Mean
53.8%
Median
1.2%
Std dev
51.4%
10th percentile
53.8%
90th percentile
51.4%
Min
51.4%53.8%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Pixtral 12BHealth & Medicine, 2409· EvalAI data53.8%
2LLaVA 1.6 34BHealth & Medicine· EvalAI data51.4%