Humanifa tops unsaturated Lean formalization benchmark with 249 problems solved
songhan_mit · x · 2026-10-21
The LeanEval team announced it has retaken first place on its lean-eval leaderboard with an updated Humanize workflow.
- LeanEval bills itself as the last unsaturated benchmark in mathematical formalization — saturating it would require formalizing Fermat's Last Theorem.
- Leaderboard: Humanifa leads with 249 solved, ahead of Axiom Prover (246), Tau/caj.al (200), Aristotle/Harmonic (162), and ByteDance's Seed Prover (156).
- The team says the new Humanize flow drew on OpenAI, Anthropic, and Axiom tech reports, with progress on 'big name theorems' coming soon.
More from Research
- Embedding arithmetic demo: cartoon − animation − comic = diagram — mayfer · 2026-10-23
- Omnii Genome: Single Generalist Model Outperforms AlphaGenome Across All Benchmarks — JosephJacks_ · 2026-10-23
- Domingos Cites New Result Claiming RL Is 'Basically Useless' vs Supervised Learning — pmddomingos · 2026-10-23
- Word Arithmetic on Embeddings: "Bathroom Minus Toilet Equals Kitchen" Beats SAE Probing — mayfer · 2026-10-23
- Wolfram Opens Rule 30 Prizes to AIs: $30,000 for Three Open Problems — cephaloform · 2026-10-23
- Stanford and Databricks use AI agents to reproduce medical findings and test analytical robustness — ChengleiSi · 2026-10-23