EgoCoT-Bench - Goal-Oriented Object Tracking: leaderboard
EgoCoT-Bench (2026) Goal-Oriented Object Tracking subtask: from an egocentric manipulation video, track an object by its functional role in the manipulation goal. 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), Goal-Oriented Object Tracking subtask (track an object by its functional role in the manipulation goal); 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 | GPT-5.1 | 45.28 | #248 |
| 2 | GPT-5.2 | 42.92 | #190 |
| 3 | Qwen 3.5 397B A17B | 38.68 | #270 |
| 4 | InternVL3.5-4B | 38.21 | #1946 |
| 5 | InternVL3.5-14B | 36.79 | #1519 |
| 6 | Qwen 3.5 Plus | 35.85 | #250 |
| 7 | Qwen 3.5 27B | 34.43 | #380 |
| 8 | Qwen 3 VL Plus | 32.7 | #514 |
| 9 | InternVL3.5-1B | 32.55 | #6140 |
| 10 | Qwen 3.5 122B A10B | 30.19 | #350 |
| 11 | Qwen 3 VL 32B | 27.83 | #624 |
| 12 | Qwen 3 VL 235B A22B | 27.36 | #486 |
| 13 | InternVL3.5-2B | 26.42 | #3313 |
| 14 | InternVL3.5-8B | 25.94 | #1618 |
| 15 | Qwen 3 VL 8B | 25 | #927 |
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-goal-oriented-object-tracking · How It Works · Data refreshed daily, snapshot 2026-11-22.