Lean AI Formalization Leaderboard: leaderboard
Submission-based Lean formalization leaderboard for hard mathematical problems where accepted solutions must pass automated comparator verification.
Metric: Solved Problems. Source: lean-lang.org. Source: lean-lang.org. 76 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 112 | #19 |
| 2 | GPT-5.5 | 16 | #31 |
| 3 | Claude Opus 5 | 6 | #12 |
| 4 | Claude Fable 5 | 5 | #16 |
| 5 | DeepSeek V4 Flash | 3 | #137 |
| 6 | Grok 4.5 | 3 | #48 |
| 7 | Gemini 3.1 Pro (Preview) | 2 | #58 |
| 8 | GPT-5 | 1 | #98 |
| 9 | Claude Opus 4.7 | 1 | #49 |
| 10 | Hy3 | 1 | #93 |
| 11 | GPT-5 Codex | 1 | #127 |
Interactive version: theaggregate.ai/benchmark?slug=lean-ai-formalization-leaderboard · How It Works · Data refreshed daily, snapshot 2026-10-20.