JetBrains-Research/SWE-TaskFlow-SWE-Bench-Pro-Trajectories download history

JetBrains-Research/SWE-TaskFlow-SWE-Bench-Pro-Trajectories is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 3,334 times (435 in the last 7 days), and 3,851 times in total. It ranks #11,095 among datasets by monthly downloads.

SWE-TaskFlow: SWE-Bench Pro Agent Runs This dataset contains the agent runs behind the Single → Split → Split+QA experiment in “Coding-Agent Benchmarks Should Match Their Users’ Task Flows” by Igor Slinko, Yaroslav Golubev, and Sergey Titov. It is a companion to JetBrains-Research/SWE

Open JetBrains-Research/SWE-TaskFlow-SWE-Bench-Pro-Trajectories on Hugging Face

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