LLM2014 Logic 2025-01 — leaderboard
Metric: Score (%). Source: raw.githubusercontent.com. 29 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O1 | 91.91 |
| 2 | DeepSeek R1 | 84.16 |
| 3 | O1 Mini | 74.15 |
| 4 | DeepSeek V3 | 54.67 |
| 5 | Gemini 2.0 Flash | 47.59 |
| 6 | MiniMax-Text-01 | 38.04 |
| 7 | Yi Lightning | 35.47 |
| 8 | Llama 3.1 405B | 31.93 |
| 9 | Mistral Large 2 (Nov) Instruct (2411) | 26.84 |
| 10 | GPT-4o Mini | 21.25 |
Interactive version: theaggregate.ai/benchmark?slug=llm2014-logic-2025-01 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.