OmniCoT - CoT F1: leaderboard

Metric: Chain-of-thought F1 x100 (0-100): MME-CoT harmonic mean of step precision (faithfulness) and recall of reference solution steps, scored by an LLM judge 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 2031. 21 models tracked.

Top models

#ModelScore
1GPT-541.51
2Qwen 3 VL 8B Instruct39.8
3Grok 436.4
4Qwen 2.5 VL 72B Instruct35.39
5Seed 1.835.13
6Gemini 3 Flash35.01
7Qwen 2.5 VL 32B Instruct33.17
8ChatGPT 4o31.87
9GLM-4.5V31.12
10Qwen 2.5 VL 7B Instruct25.76

Interactive version: theaggregate.ai/benchmark?slug=omnicot-cot-f1 · How It Works · Data refreshed daily, snapshot 2026-09-29.