OmniCoT: leaderboard
Metric: Overall accuracy (%), question-weighted over the See, Locate and Move dimensions, 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 2030. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 39.72 |
| 2 | Seed 1.8 | 38.9 |
| 3 | Qwen 2.5 VL 72B Instruct | 35.26 |
| 4 | Grok 4 | 34.99 |
| 5 | Qwen 2.5 VL 32B Instruct | 32.39 |
| 6 | ChatGPT 4o | 31.58 |
| 7 | GLM-4.5V | 29.95 |
| 8 | Gemini 3 Flash | 28.43 |
| 9 | Qwen 3 VL 8B Instruct | 27.56 |
| 10 | Qwen 2.5 VL 7B Instruct | 23.53 |
Interactive version: theaggregate.ai/benchmark?slug=omnicot · How It Works · Data refreshed daily, snapshot 2026-09-29.