EgoCoT-Bench - Predictive and Causal Inference: 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), Predictive and Causal Inference group (next state and next action anticipation and local cause-outcome inference); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 Plus | 78.21 |
| 2 | Qwen 3.5 27B | 77.03 |
| 3 | GPT-5.1 | 76.63 |
| 4 | Qwen 3.5 122B A10B | 76.32 |
| 5 | Qwen 3.5 397B A17B | 76.11 |
| 6 | GPT-5.2 | 75.68 |
| 7 | Qwen 3 VL 235B A22B | 73.37 |
Interactive version: theaggregate.ai/benchmark?slug=egocot-bench-predictive-and-causal-inference · How It Works · Data refreshed daily, snapshot 2026-10-07.