Benchmark
MMAU Sound
Scores are percentages.
- Models measured
- 6
- Scores recorded
- 11
- Sources
- 2
- IQ weight
- 0.71
Score distribution
- 68.2%
- Mean
- 68.9%
- Median
- 4.1%
- Std dev
- 62.7%
- 10th percentile
- 73.3%
- 90th percentile
- 62.5%
- Min
This benchmark has a weight of 0.71 for chat models, measured over 5 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 2.5 ProTest-mini· MMAU (audio) data | 75.1% |
| 2 | Gemini 2.5 FlashTest-mini· MMAU (audio) data | 73.3% |
| 3 | Gemini 2.0 FlashTest-mini· MMAU (audio) data | 71.2% |
| 4 | Gemini 2.5 ProTest· MMAU (audio) data | 70.6% |
| 5 | Gemini 2.5 FlashTest· MMAU (audio) data | 69.5% |
| 6 | Gemini 2.0 FlashTest· MMAU (audio) data | 68.9% |
| 7 | Qwen2.5-Omni 7B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 67.9% |
| 8 | Phi 4 Multimodal InstructTest-mini· MMAU (audio) data | 65.5% |
| 9 | Gemini 2.5 Flash-LiteTest-mini· MMAU (audio) data | 63.1% |
| 10 | Phi 4 Multimodal InstructTest· MMAU (audio) data | 62.7% |
| 11 | Gemini 2.5 Flash-LiteTest· MMAU (audio) data | 62.5% |
Data credits: Data by LLM Stats