rl-rag/browsecomp-high-effort-gpt-oss-120b download history

rl-rag/browsecomp-high-effort-gpt-oss-120b is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,377 times (198 in the last 7 days), and 7,430 times in total. It ranks #15,188 among datasets by monthly downloads.

browsecomp-high-effort-gpt-oss-120b Deep research agent evaluation on data/browsecomp.jsonl (normal split). Results Metric Value pass@4 44.1% avg@4 22.9% Trajectory accuracy 22.9% (1158/5064) Questions 1266 Trajectories 5064 (4 per question) Avg tool calls

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

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