Benchmark
MMAU-Pro
Scores are percentages. Higher is better.
- Models measured
- 12
- Scores recorded
- 12
- Sources
- 2
- IQ weight
- 1.37
Score distribution
- 59.5%
- Mean
- 62.9%
- Median
- 11.6%
- Std dev
- 39.7%
- 10th percentile
- 70.4%
- 90th percentile
- 35.4%
- Min
This benchmark has a weight of 1.37 for chat models, measured over 10 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 |
|---|---|---|
| 1 | Gemini 3.1 Pro Preview· MMAU-Pro data | 72.2% |
| 2 | Gemini 3.7 Flash· MMAU-Pro data | 70.4% |
| 3 | Gemini 3.6 Flash· MMAU-Pro data | 69.6% |
| 4 | MiMo V2 OmniXiaomi MiMo-V2-Omni release table · audio understanding and reasoning· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 69.4% |
| 5 | Gemini 3.5 Flash· MMAU-Pro data | 68.5% |
| 6 | qwen3-omni-30b-a3b-instruct· MMAU-Pro data | 62.9% |
| 7 | Gemini 2.5 Flash· MMAU-Pro data | 59.2% |
| 8 | GPT Audio· MMAU-Pro data | 58.8% |
| 9 | Gemini 2.0 Flash· MMAU-Pro data | 55.7% |
| 10 | Qwen2.5-Omni 7B· MMAU-Pro data | 52.2% |
| 11 | Gemma 3n E4B IT· MMAU-Pro data | 39.7% |
| 12 | Gemma 3n E2b It· MMAU-Pro data | 35.4% |