TraceAV-Bench (Audio Only): leaderboard
TraceAV-Bench (2026), long audio-visual video questions with multi-hop evidence, answered from the audio track alone: audio models and omni models with the visual stream removed. The score is accuracy in percent, the macro-average of 12 general sub-tasks; higher is better.
Metric: Accuracy (%), macro-average of the 12 general sub-tasks, four-option multiple choice over long audio-visual videos (10 to 140 minutes), exact match of the selected option set, each model at its official inference setting, with audio input only (audio LLMs, and omni models with the visual stream removed); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 3 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Ming-Flash-Omni-2.0 | 30.78 | #1266 |
| 2 | Qwen2-Audio-7B | 30.74 | |
| 3 | Qwen 3 Omni 30B A3B | 30.36 | #847 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=traceav-bench-audio-only · How It Works · Data refreshed daily, snapshot 2026-11-21.