ProofBench

Private 100-problem Lean 4 suite: given a natural-language statement and a formal theorem, the model must write a proof the checker accepts.

Also known as: FormalProofBench, Proof Bench, ProofBench v1.1

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorymath
SubcategoryLean 4 graduate-level formal theorem proving
Page statusactive
Metricproof success rate
Directionhigher_is_better
Unit%
Dataset size100
PublisherVals AI

What it measures

ProofBench (Vals AI; paper title FormalProofBench) tests whether a model can turn graduate-level math into a machine-checked Lean 4 proof. Each item pairs an English problem with a vetted Lean statement. The model may search Mathlib and run Lean, then must submit one proof. The checker either accepts it or not. There is no partial credit for a plausible write-up. Problems come from qualifying exams and textbooks across analysis, algebra, probability, number theory, and logic, not from contest short-answer keys.

Task format

Agentic loop with lean_loogle, lean_run_code, and a single submit_proof. Up to 40 turns (Epoch and Vals write-ups). Natural-language statement plus Lean 4 theorem in; compiled proof out.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub