CLoud5-real/longrca-bench download history

CLoud5-real/longrca-bench is an other dataset on the Hugging Face Hub. In the last 30 days it was downloaded 612 times (221 in the last 7 days), and 960 times in total. It ranks #28,140 among datasets by monthly downloads.

LongRCA Bench A benchmark for diagnosing responsible roles and root causes in long-horizon agent failures. 1,140 observed, non-injected failed trajectories from SWE-bench Pro, Terminal-Bench 2, TravelPlanner, VitaBench, and WebArena Verified. Human annotations identifying the respons

Open CLoud5-real/longrca-bench on Hugging Face

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