TraceAV-Bench: leaderboard
TraceAV-Bench (2026) tests multi-hop trajectory reasoning over long audio-visual videos: four-option questions whose answers chain several timestamped audio and visual evidence hops across videos of 10 to 140 minutes. The score is accuracy in percent, the macro-average of 12 general sub-tasks with full audio and video input; 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 the full audio and video input; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 68.29 | #102 |
| 2 | Gemini 2.5 Pro | 63.52 | #280 |
| 3 | Gemini 3 Flash | 62.28 | #180 |
| 4 | Gemini 2.5 Flash | 59.04 | #466 |
| 5 | Ming-Flash-Omni-2.0 | 51.7 | #1258 |
| 6 | Gemini 2.0 Flash | 51.59 | #731 |
| 7 | Qwen 3 Omni 30B A3B | 48.43 | #851 |
| 8 | OmniVinci-9B | 47.38 | |
| 9 | MiniCPM-o-4.5 | 44.83 | #1251 |
| 10 | Qwen2.5-Omni-7B | 42.06 | #1888 |
| 11 | Gemma 4 E4B | 40.93 | #2199 |
| 12 | video-SALMONN 2 | 38.63 | #2695 |
| 13 | HumanOmni-7B | 38.5 | #3241 |
| 14 | VideoLLaMA2.1-7B-AV | 30.43 | #4199 |
| 15 | Baichuan-Omni-1.5 | 26.91 | #3189 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=traceav-bench · How It Works · Data refreshed daily, snapshot 2026-11-22.