Benchmark
MAEB(v1) - AudioMultilabelClassification
Scores are percentages.
- Models measured
- 11
- Scores recorded
- 11
- Sources
- 1
- IQ weight
- 0.57
Score distribution
- 41.8%
- Mean
- 46.3%
- Median
- 20.3%
- Std dev
- 13%
- 10th percentile
- 69.3%
- 90th percentile
- 9.8%
- Min
This benchmark has a weight of 0.57 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 | Jina Embeddings v5 Omni NanoAudioMultilabelClassification· MTEB Multimodal Boards data docs | 70.8% |
| 2 | Jina Embeddings v5 Omni SmallAudioMultilabelClassification· MTEB Multimodal Boards data docs | 69.3% |
| 3 | Whisper MediumAudioMultilabelClassification· MTEB Multimodal Boards data docs | 56.8% |
| 4 | Whisper SmallAudioMultilabelClassification· MTEB Multimodal Boards data docs | 51.4% |
| 5 | Whisper Large V3AudioMultilabelClassification· MTEB Multimodal Boards data docs | 47.6% |
| 6 | Whisper BaseAudioMultilabelClassification· MTEB Multimodal Boards data docs | 46.3% |
| 7 | Whisper TinyAudioMultilabelClassification· MTEB Multimodal Boards data docs | 41.4% |
| 8 | embeddinggemma-2AudioMultilabelClassification· MTEB Multimodal Boards data docs | 38.8% |
| 9 | Qwen3 Omni 30B A3B ThinkingAudioMultilabelClassification· MTEB Multimodal Boards data docs | 15.2% |
| 10 | qwen3-omni-30b-a3b-instructAudioMultilabelClassification· MTEB Multimodal Boards data docs | 13% |
| 11 | Qwen2.5-Omni 7BAudioMultilabelClassification· MTEB Multimodal Boards data docs | 9.8% |