Reproduce “Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Koutian Wu, Wenjun Zhang, Junjie Zhou, Pengqian Han, Qiming Bao, Ergan Shang, Jiayu Wang, Junkai Wang and 8 more
Benchmark Radar brings daily benchmark discoveries together with benchmark records and model-report evidence, while retaining links to papers, repositories, and datasets. Its catalog contains 1,283 source records, including 464 of 493 records without numeric scores that link to an artifact. In a worked prior-art search, a contributor verified two candidate papers; retrieval precision, suitability, and time saved remain unevaluated.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.