NJU-LINK/TELBench download history

NJU-LINK/TELBench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 433 times (119 in the last 7 days), and 11,753 times in total. It ranks #37,063 among datasets by monthly downloads.

TELBench TELBench is a 1,000-instance benchmark for span-level error localization in deep-research agent trajectories. Each instance contains a task question, ordered semantic spans, and expert-verified error span labels. The full JSONL release is encrypted so that Hugging Face's data

Open NJU-LINK/TELBench on Hugging Face

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