PutnamBench - Lean 4, Answer Supplied (pass@1; Revision 0da3032; FTPEvals): leaderboard
Number of Putnam competition problems reported solved in Lean 4, with numerical answers supplied in the theorem statement where required. The source reports compute budget 'pass@1'. Higher is better; counts stay separate from other languages, answer conditions and budgets. Reported corpus revision: 0da3032. Harness: FTPEvals.
Metric: Problems solved; Lean 4, Answer Supplied; reported compute budget: pass@1; Revision 0da3032; FTPEvals. Source: github.com. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 3 | #121 |
| 2 | O4 Mini (High) | 2 | #174 (O4 Mini) |
| 3 | DeepSeek R1 | 1 | #246 |
| 4 | Claude 3.7 Sonnet | 0 | #244 |
| 5 | DeepSeek V3 (0324) | 0 | #331 |
| 6 | O3 Mini | 0 | #265 |
| 7 | Grok 3 Mini | 0 | #277 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=putnambench-lean-4-answer-supplied-pass-1-revision-0da3032-ftpevals · How It Works · Data refreshed daily, snapshot 2026-10-16.