TOC-Bench - Duration Category: leaderboard
The duration category questions of TOC-Bench (2026), video questions grounded in per-frame object tracks and kept only when not answerable from text alone, single frames or shuffled frames: how long an object event lasts, from very briefly to an extended period. Accuracy in percent; higher is better.
Metric: Duration Category accuracy (%) on TOC-Bench (2,323 human-verified questions over 1,951 videos from Charades, Perception Test, OVIS and MOSE, grounded in per-frame object tracks and kept only when not answerable from text alone, single frames or shuffled frames), mostly 32 uniformly sampled frames, deterministic scoring of multiple-choice, statement-pair, numeric and ordering formats; higher is better. Source: arxiv.org. Saturation forecast: Around September 2027. 21 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 44.6 | #54 |
| 2 | Seed 2.0 Lite | 43.9 | #300 |
| 3 | GLM-5V Turbo | 42.3 | #360 |
| 4 | Gemini 3.1 Pro (Preview) | 40.1 | #99 |
| 5 | Grok 4.3 | 39.7 | #342 |
| 6 | Kimi K2.6 | 30.1 | #192 |
| 7 | Gemini 3.1 Flash Lite (Preview) | 30.1 | #417 |
| 8 | Qwen 2.5 VL 72B | 30.1 | #781 |
| 9 | MiMo-V2-Omni | 26.9 | #465 |
| 10 | Qwen 3 VL 8B (Thinking) | 24.7 | #910 |
| 11 | Video-LLaVA-7B | 23.7 | #3879 |
| 12 | GPT-5.4 Mini | 21.8 | #406 |
| 13 | LLaVA-Video-7B | 21.5 | #2276 |
| 14 | LLaVA-Video-72B | 21.5 | #1193 |
| 15 | InternVL3-8B | 20.2 | #1782 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=toc-bench-duration-category · How It Works · Data refreshed daily, snapshot 2026-11-21.