VCR-Bench - CoT Score: leaderboard
On the same 1,034 video questions, GPT-4o splits each answer into steps and matches them against human-checked reference steps; the score is the F1 of step recall and step precision. Unlike the VCR-Bench accuracy board, a right answer reached by wrong or missing steps scores low.
Metric: CoT score (F1, %). Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 VL 72B Instruct | 50.5 | #849 |
| 2 | Qwen 2.5 VL 7B Instruct | 38.2 | #1893 |
| 3 | MiniCPM-o-2.6 | 33.8 | #2417 |
| 4 | InternVL2.5-78B | 33.7 | #1036 |
| 5 | LLaVA-Video-72B-Qwen2 | 33.6 | #1344 |
| 6 | Aria | 33.5 | #2189 |
| 7 | VideoLLaMA3-7B | 32 | #2015 |
| 8 | InternVL2.5-8B | 28 | #2401 |
| 9 | InternVideo2.5-Chat-8B | 21.2 | #2031 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=vcr-bench-cot-score · How It Works · Data refreshed daily, snapshot 2026-11-17.