TraceAV-Bench - Speech Context: leaderboard
The Speech Context sub-task of TraceAV-Bench (2026), part of its audio-centric reasoning dimension: multiple-choice questions over long videos whose answers chain several timestamped evidence hops. The score is accuracy in percent with full audio and video input; higher is better.
Metric: Accuracy (%) on the 130 Speech Context (SC) questions, 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 the full audio and video input; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 96.92 | #99 |
| 2 | Gemini 3 Flash | 86.92 | #175 |
| 3 | Gemini 2.5 Pro | 83.85 | #276 |
| 4 | Gemini 2.5 Flash | 81.54 | #463 |
| 5 | Gemini 2.0 Flash | 70 | #723 |
| 6 | OmniVinci-9B | 65.38 | |
| 7 | Qwen 3 Omni 30B A3B | 63.85 | #847 |
| 8 | Ming-Flash-Omni-2.0 | 63.85 | #1266 |
| 9 | MiniCPM-o-4.5 | 61.54 | #1252 |
| 10 | Qwen2.5-Omni-7B | 60 | #1884 |
| 11 | Gemma 4 E4B | 55.38 | #2184 |
| 12 | HumanOmni-7B | 52.31 | #3308 |
| 13 | video-SALMONN 2 | 47.69 | #2687 |
| 14 | VideoLLaMA2.1-7B-AV | 36.15 | #4204 |
| 15 | Baichuan-Omni-1.5 | 32.31 | #3285 |
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-speech-context · How It Works · Data refreshed daily, snapshot 2026-11-21.