Benchmark
MMMU (val)
Vision benchmarks measure how well models understand images. Scores are percentages.
- Models measured
- 58
- Scores recorded
- 60
- Sources
- 2
- IQ weight
- 0.92
Score distribution
- 60.9%
- Mean
- 60.6%
- Median
- 12.4%
- Std dev
- 47.4%
- 10th percentile
- 76%
- 90th percentile
- 23.7%
- Min
This benchmark has a weight of 0.92 for chat models, measured over 58 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 51 | Gemma 3 4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 48.8% |
| 52 | InternVL2 4B· OpenVLM Leaderboard data | 48.3% |
| 53 | Llama 3.2 11B Vision Instruct· OpenVLM Leaderboard data | 48% |
| 54 | Claude 3 Sonnet· OpenVLM Leaderboard data | 47.4% |
| 55 | Gemma 3 4B· OpenVLM Leaderboard data | 47.3% |
| 56 | GLM 4 Vision· OpenVLM Leaderboard data | 45.6% |
| 57 | Phi-3.5 Vision Instruct· OpenVLM Leaderboard data | 44.6% |
| 58 | Qwen-VL Plus· OpenVLM Leaderboard data | 39.8% |
| 59 | Moondream2· OpenVLM Leaderboard data | 29.3% |
| 60 | kosmos-2· OpenVLM Leaderboard data | 23.7% |
Showing 51–60 of 60 results.
Data credits: OpenVLM Leaderboard (OpenCompass / VLMEvalKit), Apache-2.0 (licence) · Data by LLM Stats