AudioBench - LibriSpeech Clean WER — leaderboard
Metric: WER (%) (lower is better). Source: github.com. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Phi-4 Multimodal Instruct | 1.68 |
| 2 | Qwen2-Audio-7B-Instruct | 3.51 |
| 3 | SALMONN-7B | 10.27 |
Interactive version: theaggregate.ai/benchmark?slug=audiobench-librispeech-clean-wer · How the rankings work · Data refreshed daily, snapshot 2026-07-22.