CCTVBench - Balanced Accuracy: leaderboard

CCTVBench (2026) plain binary classification quality: balanced accuracy (%) over all 7,104 yes/no video-question instances of real and counterfactual traffic videos; proprietary API models answer each video's questions in one batched request; higher is better.

Metric: Balanced accuracy (%) over all binary video-question instances of 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, proprietary models answer per-video batches, parsed as independent binary responses; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 10 models tracked. Updated 14 Nov 2026.

Top models

#ModelScoreOverall rank
1InternVL3.5-8B64.85#1604
2Qwen 3 VL 2B62.96#2134
3Qwen 3 VL 8B60.26#917
4PLLaVA-13B59.81#3377
5VideoLLaMA3-7B58.47#2050
6InternVL3.5-2B58.46#3284
7PLLaVA-7B57.38#5139
8Phi-4 Multimodal Instruct57.07#4154
9VideoLLaMA3-2B55.38#2593
10Video-ChatGPT49.85#6929

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=cctvbench-balanced-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-21.