Loading...
Loading...
Available on 1 platform
Sign in to view source links and access this dataset
QEDBench is a benchmark for evaluating large language models on formal proof generation and evaluation. It contains 272 proof-based problems spanning 10 distinct mathematical domains, created by researcher Quanquan C. Liu. The dataset was published in February 2026.
License details are not explicitly provided in the input; check the dataset page for terms. The primary use is for evaluation, not as a general-purpose training corpus.