File eval_imobench_proof.py

scripts/eval_imobench_proof.py:None–None · view source on GitHub ↗

Source from the content-addressed store, hash-verified

1	"""
2	Evaluation script for IMO-Bench ProofBench dataset (60 problems)
3	Tests model performance on rigorous mathematical proof construction
4	Uses IMO25-style verification system for grading

nothing calls this directly

mainFunction · 0.70

no test coverage detected