EgoCoT-Bench - Manipulation State Perception: leaderboard
EgoCoT-Bench (2026) Manipulation State Perception subtask: from an egocentric manipulation video, recognize the current manipulation state of the object. 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), Manipulation State Perception subtask (recognize the current manipulation state of the object); 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 397B A17B | 87.79 | #270 |
| 2 | Qwen 3.5 122B A10B | 86.38 | #350 |
| 3 | Qwen 3.5 Plus | 85.92 | #250 |
| 4 | Qwen 3.5 27B | 84.51 | #380 |
| 5 | Qwen 3 VL 30B A3B | 82.16 | #791 |
| 6 | Qwen 3 VL 8B | 81.6 | #927 |
| 7 | Qwen 3 VL 32B | 79.81 | #624 |
| 8 | InternVL3.5-2B | 79.81 | #3313 |
| 9 | GPT-5.1 | 77 | #248 |
| 10 | Qwen 3 VL 235B A22B | 77 | #486 |
| 11 | Qwen 3 VL Plus | 77 | #514 |
| 12 | InternVL3.5-14B | 75.12 | #1519 |
| 13 | LLaVA-OneVision-1.5-8B | 74.65 | #1876 |
| 14 | InternVL3.5-4B | 73.24 | #1946 |
| 15 | GPT-5.2 | 72.3 | #190 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=egocot-bench-manipulation-state-perception · How It Works · Data refreshed daily, snapshot 2026-11-22.