EgoCoT-Bench - Location and Visibility Retrospection: leaderboard
Metric: Answer accuracy (%, four-way multiple choice, strict exact match) of zero-shot MLLMs on egocentric manipulation videos of EgoCoT-Bench (351 clips, 3,172 human-verified questions built from spatio-temporal scene graphs), Location and Visibility Retrospection subtask (recover an earlier location or visibility of an object); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 27B | 67.74 |
| 2 | Qwen 3.5 122B A10B | 62.7 |
| 3 | Qwen 3.5 Plus | 60.69 |
| 4 | GPT-5.2 | 59.88 |
| 5 | Qwen 3.5 397B A17B | 59.07 |
| 6 | Qwen 3 VL 235B A22B | 52.82 |
| 7 | GPT-5.1 | 49.4 |
Interactive version: theaggregate.ai/benchmark?slug=egocot-bench-location-and-visibility-retrospection · How It Works · Data refreshed daily, snapshot 2026-10-07.