Open-Eval-Commons/OpenBenchmarks download history
Open-Eval-Commons/OpenBenchmarks is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 10 times (4 in the last 7 days), and 116 times in total. It ranks #569,006 among datasets by monthly downloads.
Open Benchmarks Per-paper metadata for 8,045 papers whose primary contribution is an evaluation benchmark, identified by an LLM classifier from a corpus of 186,221 main-conference papers across major NLP, ML, AI, and computer-vision venues, plus a small human-labelled set of arXiv-onl