phylobio/BixBench-Verified-50 download history

phylobio/BixBench-Verified-50 is a question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 615 times (117 in the last 7 days), and 4,159 times in total. It ranks #28,039 among datasets by monthly downloads.

BixBench-Verified-50 A curated subset of BixBench with 50 verified questions across 33 unique data capsules, designed for reliable evaluation of AI agents on computational biology tasks. Overview BixBench-Verified-50 was created to isolate real agent performance from benchmark

Open phylobio/BixBench-Verified-50 on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.