LLM2014 Logic 2025-11: leaderboard
Metric: Median Score. Source: raw.githubusercontent.com. 53 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 (High) | 83.75 |
| 2 | Gemini 3 Pro | 83.55 |
| 3 | GPT-5.1 (High) | 79.53 |
| 4 | GPT-5 Mini (High) | 76.15 |
| 5 | Grok 4 | 69.52 |
| 6 | Claude Sonnet 4.5 (Thinking) | 66.7 |
| 7 | Kimi K2 (Thinking) | 64.58 |
| 8 | Grok 4.1 Fast (Reasoning) | 62.78 |
| 9 | Grok 4 Fast (Reasoning) | 62.72 |
| 10 | Qwen 3 Max (Thinking) | 53.6 |
| 11 | Qwen 3 235B A22B 2507 (Thinking) | 51.81 |
| 12 | DeepSeek V3.2 (Thinking) | 50.77 |
| 13 | Gemini 2.5 Pro | 47.67 |
| 14 | GPT-OSS-120B (High) | 47.57 |
| 15 | Qwen 3 Max | 46.94 |
Interactive version: theaggregate.ai/benchmark?slug=llm2014-logic-2025-11 · How It Works · Data refreshed daily, snapshot 2026-09-05.