Qwen-Audio-Chat: benchmark results
Provider: Alibaba. Access: Open.
Unified ELO 1324 ± 23, rank #2375 of 2656 rated models, from 70 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AudioBench - VoxCeleb Accent | 48.05 | Mean Score (%) | 100 |
| AudioBench - AudioCaps Captioning | 37.3 | Mean Score (%) | 87.5 |
| AudioBench - Clotho AQA | 61.93 | Mean Score (%) | 87.5 |
| AudioBench - IMDA AR Dialogue | 66.67 | Mean Score (%) | 87.5 |
| AudioBench - MELD Emotion | 50.73 | Mean Score (%) | 87.5 |
| AudioBench - AudioCaps QA | 50.22 | Mean Score (%) | 75 |
| AudioBench - MuChoMusic | 59.06 | Score (%) | 75 |
| AudioBench - WavCaps Captioning | 28.24 | Mean Score (%) | 75 |
| AudioBench - LibriSpeech Clean WER | 2.03 | WER (%) (lower is better) | 66.7 |
| AudioBench - TED-LIUM 3 WER | 4.05 | WER (%) (lower is better) | 66.7 |
| AudioBench - IMDA AR Sentence | 3.93 | Mean Score (%) | 62.5 |
| AudioBench - IMDA GR Sentence | 57.55 | Mean Score (%) | 62.5 |
Interactive version: theaggregate.ai/model?slug=qwen-audio-chat · How It Works · Data refreshed daily, snapshot 2026-09-19.