LongCoT-mini - Computer Science: leaderboard
Long-horizon chain-of-thought reasoning on the easier computer science problems of LongCoT-mini (2026), the small companion set of LongCoT, single attempt without tools at the highest available reasoning setting. Accuracy in percent; higher is better.
Metric: Accuracy (%) on the easy computer science problems of LongCoT-mini (long-horizon chain-of-thought problems with short inputs and verifiable answers), single-shot, highest available reasoning setting up to the provider output limit, no tools; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5.2 | xHigh | 44.4 | #190 |
| 2 | Gemini 3 Pro | 17.1 | #146 | |
| 3 | DeepSeek V3.2 | Thinking | 13.9 | #425 |
| 4 | Claude Sonnet 4.5 | Thinking | 12.4 | #267 |
| 5 | Grok 4.1 Fast | Reasoning | 12.1 | #431 |
| 6 | Kimi K2 (Thinking) | 11.4 | ||
| 7 | GLM-4.7 | 8.6 | #383 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=longcot-mini-computer-science · How It Works · Data refreshed daily, snapshot 2026-11-22.