AudioBench - CNA WER — leaderboard
Metric: WER (%) (lower is better). Source: github.com. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | cascade_whisper_large_v3_llama_3_8b_instruct | 13.8 |
| 2 | whisper_large_v3 | 13.84 |
| 3 | cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct | 15.17 |
| 4 | SALMONN_7B | 15.4 |
| 5 | MERaLiON-AudioLLM-Whisper-SEA-LION | 15.92 |
| 6 | Qwen-Audio-Chat | 19.75 |
| 7 | Qwen2-Audio-7B-Instruct | 20.68 |
| 8 | WavLLM_fairseq | 26.95 |
Interactive version: theaggregate.ai/benchmark?slug=audiobench-cna-wer · How the rankings work · Data refreshed daily, snapshot 2026-07-22.