TOC-Bench - Event Count: leaderboard
The event count 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 many times an object event repeats. Accuracy in percent; higher is better.
Metric: Event Count 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: Not forecast. 21 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | VideoLLaMA3-7B | 33.7 | #2050 |
| 2 | Video-ChatGPT | 30.7 | #6929 |
| 3 | LLaVA-Video-7B | 26.3 | #2276 |
| 4 | Seed 2.0 Lite | 24.3 | #300 |
| 5 | GPT-5.4 Mini | 21.3 | #406 |
| 6 | Grok 4.3 | 19.7 | #342 |
| 7 | Kimi K2.6 | 19.3 | #192 |
| 8 | Gemini 3.1 Pro (Preview) | 18.7 | #99 |
| 9 | InternVL3-8B | 18.7 | #1782 |
| 10 | MiniCPM-V-2.6 | 18.7 | #3267 |
| 11 | GPT-5.5 | 18.3 | #54 |
| 12 | LLaVA-Video-72B | 15 | #1193 |
| 13 | Qwen 3 VL 8B (Thinking) | 14 | #910 |
| 14 | GLM-5V Turbo | 13.7 | #360 |
| 15 | VideoChat-R1.5-7B | 7 | #1254 |
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-event-count · How It Works · Data refreshed daily, snapshot 2026-11-21.