OmniCoT - Move: leaderboard

Metric: Accuracy (%) on Move questions (translational and rotation-translational movement simulation) with chain-of-thought prompting on OmniCoT-B (synthetic 360-degree equirectangular panoramas with three anchor objects given by coordinates and orientation); answers are object identities, visibility, directions or the closest angle option, exact match after normalization. Source: arxiv.org. Saturation forecast: Around 2029. 21 models tracked.

Top models

#ModelScore
1GPT-542.71
2Seed 1.841.14
3Grok 437.04
4Qwen 2.5 VL 72B Instruct35.05
5ChatGPT 4o33.65
6Qwen 2.5 VL 32B Instruct31.99
7Gemini 3 Flash29.29
8GLM-4.5V28.6
9Qwen 3 VL 8B Instruct26.59
10Qwen 2.5 VL 7B Instruct24.33

Interactive version: theaggregate.ai/benchmark?slug=omnicot-move · How It Works · Data refreshed daily, snapshot 2026-09-29.