CCTVBench: leaderboard
CCTVBench (2026) tests video LLMs on 305 real traffic-accident videos paired with generated counterfactual videos and mutually exclusive yes/no hypotheses; a question pair counts only when all four video-question answers are consistent. Quadruple accuracy (%), one question per request; higher is better.
Metric: Quadruple accuracy (%): share of question pairs in which the model answers Yes to the true hypothesis on the real video and No to the other three video-question combinations, on CCTVBench's 305 contrastive traffic scenes (a real accident video paired with a world-model-generated counterfactual video) and 1,776 pairs of mutually exclusive yes/no hypothesis questions (7,104 binary instances), single-word Yes/No answers at temperature 0, each question in its own request; higher is better. Source: arxiv.org. Saturation forecast: Around April 2028. 10 models tracked. Updated 14 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | InternVL3.5-8B | 11.38 | #1604 |
| 2 | Qwen 3 VL 8B | 10.65 | #917 |
| 3 | Qwen 3 VL 2B | 7.62 | #2134 |
| 4 | InternVL3.5-2B | 7.05 | #3284 |
| 5 | VideoLLaMA3-7B | 6.58 | #2050 |
| 6 | VideoLLaMA3-2B | 6.48 | #2593 |
| 7 | PLLaVA-13B | 6.19 | #3377 |
| 8 | Video-ChatGPT | 4.13 | #6929 |
| 9 | PLLaVA-7B | 3.9 | #5139 |
| 10 | Phi-4 Multimodal Instruct | 2.92 | #4154 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=cctvbench · How It Works · Data refreshed daily, snapshot 2026-11-21.