Benchmark
MAEB(v1, audio-only) - AudioClustering
Scores are percentages.
- Models measured
- 11
- Scores recorded
- 11
- Sources
- 1
- IQ weight
- 0.00
Score distribution
- 3.8%
- Mean
- 3.9%
- Median
- 2.2%
- Std dev
- 0.74%
- 10th percentile
- 6.1%
- 90th percentile
- 0.69%
- Min
This benchmark has a weight of 0.00 for speech 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 | Whisper TinyAudioClustering· MTEB Multimodal Boards data docs | 7.4% |
| 2 | Jina Embeddings v5 Omni SmallAudioClustering· MTEB Multimodal Boards data docs | 6.1% |
| 3 | Jina Embeddings v5 Omni NanoAudioClustering· MTEB Multimodal Boards data docs | 6% |
| 4 | Whisper MediumAudioClustering· MTEB Multimodal Boards data docs | 5% |
| 5 | Whisper BaseAudioClustering· MTEB Multimodal Boards data docs | 5% |
| 6 | Whisper SmallAudioClustering· MTEB Multimodal Boards data docs | 3.9% |
| 7 | Whisper Large V3AudioClustering· MTEB Multimodal Boards data docs | 3.4% |
| 8 | embeddinggemma-2AudioClustering· MTEB Multimodal Boards data docs | 2.7% |
| 9 | Qwen3 Omni 30B A3B ThinkingAudioClustering· MTEB Multimodal Boards data docs | 1.4% |
| 10 | qwen3-omni-30b-a3b-instructAudioClustering· MTEB Multimodal Boards data docs | 0.74% |
| 11 | Qwen2.5-Omni 7BAudioClustering· MTEB Multimodal Boards data docs | 0.69% |