Benchmark
MMMU - Humanities & Social Science
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
- 69.6%
- Mean
- 70.2%
- Median
- 0.6%
- Std dev
- 69%
- 10th percentile
- 70.2%
- 90th percentile
- 69%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | LLaVA 1.6 34BHumanities & Social Science· EvalAI data | 70.2% |
| 2 | Pixtral 12BHumanities & Social Science, 2409· EvalAI data | 69% |