AudioBench - IMDA Part 4 ASR WER: leaderboard
AudioBench IMDA Part 4 ASR word error rate slice measuring automatic speech-recognition transcription quality, where lower scores indicate fewer errors.
Metric: WER (%) (lower is better). Source: github.com. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen2-Audio-7B-Instruct | 56.85 | #880 |
| 2 | SALMONN-7B | 77.57 | #1293 |
| 3 | Whisper Large-v3 | 82.95 | #1271 |
| 4 | Qwen-Audio-Chat | 117.64 | #1244 |
| 5 | Phi-4 Multimodal Instruct | 138.69 | #906 |
| 6 | SeaLLMs-Audio-7B | 189.61 | #1018 |
Interactive version: theaggregate.ai/benchmark?slug=audiobench-imda-part-4-asr-wer · How It Works · Data refreshed daily, snapshot 2026-10-20.