AudioBench - IMDA Part 4 Dialogue Summarization Human: leaderboard
AudioBench IMDA Part 4 Dialogue Summarization Human slice measuring summarization quality for spoken dialogue transcripts and audio-derived conversations.
Metric: Mean Score (%). Source: github.com. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Phi-4 Multimodal Instruct | 37 | #906 |
| 2 | SeaLLMs-Audio-7B | 35.4 | #1018 |
| 3 | Qwen2-Audio-7B-Instruct | 30.3 | #880 |
| 4 | Qwen-Audio-Chat | 16 | #1244 |
| 5 | SALMONN-7B | 7 | #1293 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=audiobench-imda-part-4-dialogue-summarization-human · How It Works · Data refreshed daily, snapshot 2026-10-20.