Benchmark
MMMU (validation)
Vision benchmarks measure how well models understand images. Scores are percentages.
All vision benchmarksScores from LLM Stats data.
- Models measured
- 4
- Scores recorded
- 4
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 76.9%
- Mean
- 77.1%
- Median
- 2.7%
- Std dev
- 73.2%
- 10th percentile
- 80.7%
- 90th percentile
- 73.2%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.7% |
| 2 | Claude Opus 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77.1% |
| 3 | Claude Opus 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 76.5% |
| 4 | Claude Haiku 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 73.2% |
Data credits: Data by LLM Stats