EgoCoT-Bench - Next State Anticipation: 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), Next State Anticipation subtask (predict the most likely next state of an object); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 | 86.99 |
| 2 | Qwen 3 VL 235B A22B | 85.97 |
| 3 | Qwen 3.5 Plus | 85.2 |
| 4 | Qwen 3.5 397B A17B | 84.95 |
| 5 | GPT-5.2 | 84.69 |
| 6 | Qwen 3.5 27B | 84.65 |
| 7 | Qwen 3.5 122B A10B | 81.63 |
Interactive version: theaggregate.ai/benchmark?slug=egocot-bench-next-state-anticipation · How It Works · Data refreshed daily, snapshot 2026-10-07.