AudioBench - IMDA Part 4 Dialogue Summarization Human — leaderboard
Metric: Mean Score (%). Source: github.com. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Phi-4 Multimodal Instruct | 37 |
| 2 | Qwen2-Audio-7B-Instruct | 30.3 |
| 3 | SALMONN-7B | 7 |
Interactive version: theaggregate.ai/benchmark?slug=audiobench-imda-part-4-dialogue-summarization-human · How the rankings work · Data refreshed daily, snapshot 2026-07-22.