NJU-LINK/CodeTraceBench download history
NJU-LINK/CodeTraceBench is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 11,835 times (383 in the last 7 days), and 37,198 times in total. It ranks #2,599 among datasets by monthly downloads.
CodeTraceBench A Benchmark for Agent Trajectory Diagnosis CodeTraceBench is a large-scale benchmark of 4,316 agent trajectories with human-verified step-level annotations for evaluating trajectory diagnosis systems. Each trajectory records the full action-observation sequence of a
Spaces using CodeTraceBench
- Model Pulse 8 likes