TraceAV-Bench - Temporal Sequencing: leaderboard
The Temporal Sequencing sub-task of TraceAV-Bench (2026), part of its audio-visual joint 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 97 Temporal Sequencing (TS) 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: Around March 2027. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 63.92 | #280 |
| 2 | Gemini 3.1 Pro (Preview) | 60.82 | #102 |
| 3 | Gemini 2.5 Flash | 58.76 | #466 |
| 4 | Gemini 3 Flash | 53.61 | #180 |
| 5 | Gemini 2.0 Flash | 53.61 | #731 |
| 6 | Ming-Flash-Omni-2.0 | 53.61 | #1258 |
| 7 | Qwen 3 Omni 30B A3B | 51.55 | #851 |
| 8 | OmniVinci-9B | 44.33 | |
| 9 | video-SALMONN 2 | 41.24 | #2695 |
| 10 | Gemma 4 E4B | 38.14 | #2199 |
| 11 | MiniCPM-o-4.5 | 36.08 | #1251 |
| 12 | Qwen2.5-Omni-7B | 32.99 | #1888 |
| 13 | HumanOmni-7B | 31.96 | #3241 |
| 14 | VideoLLaMA2.1-7B-AV | 29.9 | #4199 |
| 15 | Baichuan-Omni-1.5 | 14.43 | #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-temporal-sequencing · How It Works · Data refreshed daily, snapshot 2026-11-22.