rl-rag/browsecomp-gpt-oss-120b-v2 download history

rl-rag/browsecomp-gpt-oss-120b-v2 is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 490 times (52 in the last 7 days), and 3,466 times in total. It ranks #33,653 among datasets by monthly downloads.

BrowseComp GPT-oss-120B Evaluation (v2) Deep research agent evaluation on BrowseComp using GPT-oss-120B with the elastic-serving OSS engine. Results Metric Value pass@1 37.9% Questions 1,266 Correct 480/1,266 Success rate 1132/1,266 Avg tool calls ~61 Judge

Open rl-rag/browsecomp-gpt-oss-120b-v2 on Hugging Face

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