LongCoT - Logic: leaderboard
Metric: Accuracy (%) on the medium and hard logic problems of LongCoT (main set; long-horizon chain-of-thought problems with short inputs, verifiable answers and 10K to 100K+ token reasoning), single-shot, highest available reasoning setting up to the provider output limit, no tools; higher is better. Source: arxiv.org. Saturation forecast: Around 2028. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 (xHigh) | 12 |
| 2 | Gemini 3 Pro | 1.5 |
| 3 | Claude Sonnet 4.5 (Thinking) | 0.5 |
| 4 | Kimi K2 (Thinking) | 0.5 |
| 5 | DeepSeek V3.2 (Thinking) | 0.3 |
| 6 | Grok 4.1 Fast (Reasoning) | 0 |
| 7 | GLM-4.7 | 0 |
Interactive version: theaggregate.ai/benchmark?slug=longcot-logic · How It Works · Data refreshed daily, snapshot 2026-10-07.