EgoCoT-Bench - Predictive and Causal Inference: leaderboard
EgoCoT-Bench (2026) Predictive and Causal Inference group (next state and next action anticipation and local cause-outcome inference) on egocentric manipulation videos. Four-way multiple choice accuracy in percent; higher is better.
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 February 2027. 19 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 Plus | 78.21 | #242 |
| 2 | Qwen 3.5 27B | 77.03 | #375 |
| 3 | GPT-5.1 | 76.63 | #240 |
| 4 | Qwen 3 VL 32B | 76.53 | #622 |
| 5 | Qwen 3.5 122B A10B | 76.32 | #346 |
| 6 | Qwen 3.5 397B A17B | 76.11 | #264 |
| 7 | Qwen 3 VL Plus | 76 | #512 |
| 8 | GPT-5.2 | 75.68 | #185 |
| 9 | Qwen 3 VL 235B A22B | 73.37 | #485 |
| 10 | InternVL3.5-14B | 72.53 | #1504 |
| 11 | InternVL3.5-8B | 72.42 | #1604 |
| 12 | Qwen 3 VL 8B | 71.91 | #917 |
| 13 | LLaVA-OneVision-1.5-8B | 71.79 | #1864 |
| 14 | Qwen 3 VL 30B A3B | 71.47 | #784 |
| 15 | InternVL3.5-4B | 70 | #1930 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=egocot-bench-predictive-and-causal-inference · How It Works · Data refreshed daily, snapshot 2026-11-21.