MathArena - Putnam 2025: leaderboard
William Lowell Putnam Mathematical Competition 2025: the premier US/Canada undergraduate math competition with 12 proof-based problems graded for elegance and rigor.
Metric: Accuracy (%). Source: matharena.ai. Saturation forecast: Around January 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 Pro | 77.5 | #81 |
| 2 | Gemini 3 Pro (Preview) | 75.83 | #66 |
| 3 | DeepSeek V3.2 Speciale | 59.17 | #128 |
| 4 | GPT-5.1 (High) | 48.33 | #135 (GPT-5.1) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=matharena-putnam-2025 · How It Works · Data refreshed daily, snapshot 2026-10-20.