A Lean 4 evaluation framework for theorem-proving models, with frozen targets, proof verification, and reproducible run records.
Python Updated 17 days ago 1 commits
pulse-dev|Mirror: jiaxinzhang2/formal-theorem-proving-eval-api (⭐0)
17 days agoE2B SandboxFirecracker microVMpython
No executable code files found in this repository.
About
A Lean 4 evaluation framework for theorem-proving models, with frozen targets, proof verification, and reproducible run records.
Readme