Benchmark
MMSU Phonology (Perception)
Scores are percentages.
- Models measured
- 5
- Scores recorded
- 5
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 38.3%
- Mean
- 37.3%
- Median
- 9.4%
- Std dev
- 24.5%
- 10th percentile
- 53.6%
- 90th percentile
- 24.5%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Gemini 1.5 Pro· MMSU data | 53.6% |
| 2 | Gemini 2.0 Flash· MMSU data | 41.3% |
| 3 | Qwen2.5-Omni 7B· MMSU data | 37.3% |
| 4 | Phi 4 Multimodal Instruct· MMSU data | 34.9% |
| 5 | GLM-4-Voice· MMSU data | 24.5% |