drlee1/kotraj-bench download history

drlee1/kotraj-bench is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 46 times (10 in the last 7 days), and 146 times in total. It ranks #197,310 among datasets by monthly downloads.

kotraj-bench A Korean agentic tool-use benchmark. 340 tasks across three domains, evaluated against a deterministic mock environment with a fixed user simulator. Scoring is entirely code — no LLM judge. A task succeeds only if the required tool calls were made, in the required order,

Open drlee1/kotraj-bench on Hugging Face

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