OmniCoT - See: leaderboard
Metric: Accuracy (%) on See questions (multi-step orientation tracking, relative angular calculation) 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 March 2028. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 57.29 |
| 2 | Seed 1.8 | 57.09 |
| 3 | Grok 4 | 54.4 |
| 4 | GLM-4.5V | 53.15 |
| 5 | Qwen 2.5 VL 72B Instruct | 52.03 |
| 6 | ChatGPT 4o | 51.97 |
| 7 | Qwen 2.5 VL 32B Instruct | 47.84 |
| 8 | Gemini 3 Flash | 47.52 |
| 9 | Qwen 3 VL 8B Instruct | 41.52 |
| 10 | Qwen 2.5 VL 7B Instruct | 33.77 |
Interactive version: theaggregate.ai/benchmark?slug=omnicot-see · How It Works · Data refreshed daily, snapshot 2026-09-29.