LLM2014 Logic 2025-03: leaderboard
LLM2014 monthly logic benchmark for 2025-03, reporting aggregate logical-reasoning performance on the source score scale.
Metric: Median Score. Source: raw.githubusercontent.com. Saturation forecast: Estimated already saturated. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 84.27 | #123 |
| 2 | Claude 3.7 Sonnet (Thinking) | 73.76 | #249 (Claude 3.7 Sonnet) |
| 3 | DeepSeek V3 (0324) | 57.54 | #340 |
| 4 | GPT-4.5 | 55.39 | #274 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm2014-logic-2025-03 · How It Works · Data refreshed daily, snapshot 2026-10-20.