EgoCoT-Bench - Reasoning Score: leaderboard
Metric: Reasoning score (out of 5): a Qwen-Max judge rates each generated rationale against the annotated reference reasoning for logical coherence, factual consistency and alignment with the visual evidence, 0 to 5, mean over the 3,172 questions of EgoCoT-Bench; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 27B | 2.96 |
| 2 | Qwen 3.5 122B A10B | 2.94 |
| 3 | Qwen 3.5 Plus | 2.92 |
| 4 | Qwen 3.5 397B A17B | 2.87 |
| 5 | GPT-5.2 | 2.85 |
| 6 | Qwen 3 VL 235B A22B | 2.78 |
| 7 | GPT-5.1 | 2.77 |
Interactive version: theaggregate.ai/benchmark?slug=egocot-bench-reasoning-score · How It Works · Data refreshed daily, snapshot 2026-10-07.