qqggez/QEDBench download history
qqggez/QEDBench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 26 times (5 in the last 7 days), and 95 times in total. It ranks #306,850 among datasets by monthly downloads.
QEDBench: A Benchmark for LLM Mathematical Proof Evaluation QEDBench is a challenging mathematical reasoning benchmark consisting of 272 proof-based problems spanning 10 mathematical domains, designed to evaluate LLMs on formal proof generation and evaluation. 🌐 Project Website