AudioBench - IMDA GR Sentence: leaderboard
AudioBench IMDA GR Sentence slice measuring grammar-related recognition from spoken inputs.
Metric: Mean Score (%). Source: github.com. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen2-Audio-7B-Instruct | 67.36 | #880 |
| 2 | SALMONN-7B | 59.77 | #1293 |
| 3 | Qwen-Audio-Chat | 57.55 | #1244 |
| 4 | Phi-4 Multimodal Instruct | 51.68 | #906 |
| 5 | SeaLLMs-Audio-7B | 50.08 | #1018 |
Interactive version: theaggregate.ai/benchmark?slug=audiobench-imda-gr-sentence · How It Works · Data refreshed daily, snapshot 2026-10-20.