LLM2014 Logic 2025-03 — leaderboard
Metric: Median Score. Source: raw.githubusercontent.com. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro (03-25) | 84.27 |
| 2 | Claude 3.7 Sonnet (Thinking) | 73.76 |
| 3 | DeepSeek V3 (0324) | 57.54 |
| 4 | GPT-4.5 | 55.39 |
Interactive version: theaggregate.ai/benchmark?slug=llm2014-logic-2025-03 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.