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. Status: saturation imminent. 43 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 16 |
| 2 | Claude Fable 5 | 4 |
| 3 | DeepSeek V4 Flash | 3 |
| 4 | Gemini 3.1 Pro (Preview) | 2 |
| 5 | Claude Opus 4.7 | 1 |
| 6 | Hy3 | 1 |
| 7 | GPT-5 Codex | 1 |
| 8 | Claude Sonnet 4.6 | 0 |
| 9 | Kimi K2.6 | 0 |
| 10 | DeepSeek V4 Pro | 0 |
| 11 | Mistral Large 3 | 0 |
| 12 | Grok 4.3 | 0 |
Interactive version: theaggregate.ai/benchmark?slug=lean-ai-formalization-leaderboard · How the rankings work · Data refreshed daily, snapshot 2026-07-22.