PutnamBench - Isabelle, Answer Supplied (pass@10; Revision Unspecified; T 0.1): leaderboard
Number of Putnam competition problems reported solved in Isabelle, with numerical answers supplied in the theorem statement where required. The source reports compute budget 'pass@10'. Higher is better; counts stay separate from other languages, answer conditions and budgets. A corpus revision is not reported. Reported temperature: 0.1.
Metric: Problems solved; Isabelle, Answer Supplied; reported compute budget: pass@10; Revision Unspecified; T 0.1. Source: github.com. 1 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DSP (GPT-4o) | 4 |
Interactive version: theaggregate.ai/benchmark?slug=putnambench-isabelle-answer-supplied-pass-10-revision-unspecified-t-0-1 · How It Works · Data refreshed daily, snapshot 2026-10-16.