Benchmark
MMAU-Pro Spatial
Scores are percentages.
- Models measured
- 11
- Scores recorded
- 11
- Sources
- 1
- IQ weight
- 0.90
Score distribution
- 35.1%
- Mean
- 36.3%
- Median
- 10.4%
- Std dev
- 21.8%
- 10th percentile
- 46.8%
- 90th percentile
- 12%
- Min
This benchmark has a weight of 0.90 for chat models, measured over 9 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 | 46.8% |
| 2 | Gemini 3.6 Flash· MMAU-Pro data | 46.8% |
| 3 | Gemini 3.7 Flash· MMAU-Pro data | 44.9% |
| 4 | Qwen2.5-Omni 7B· MMAU-Pro data | 41.2% |
| 5 | Gemini 3.5 Flash· MMAU-Pro data | 40.9% |
| 6 | Gemini 2.5 Flash· MMAU-Pro data | 36.3% |
| 7 | Gemini 2.0 Flash· MMAU-Pro data | 34.6% |
| 8 | GPT Audio· MMAU-Pro data | 30.2% |
| 9 | qwen3-omni-30b-a3b-instruct· MMAU-Pro data | 30.2% |
| 10 | Gemma 3n E4B IT· MMAU-Pro data | 21.8% |
| 11 | Gemma 3n E2b It· MMAU-Pro data | 12% |