OmniCoT - Locate: leaderboard

Metric: Accuracy (%) on Locate questions (multi-hop object and direction identification) 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 2034. 21 models tracked.

Top models

#ModelScore
1GPT-524.4
2Seed 1.823.87
3Qwen 2.5 VL 72B Instruct23.69
4Qwen 2.5 VL 32B Instruct21.93
5Grok 419.3
6Qwen 3 VL 8B Instruct18.73
7Qwen 2.5 VL 7B Instruct15.53
8ChatGPT 4o15.18
9GLM-4.5V15.05
10Gemini 3 Flash14.17

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