kensho/CMTBench download history
kensho/CMTBench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 21 times (5 in the last 7 days), and 459 times in total. It ranks #361,218 among datasets by monthly downloads.
(C)MT-Bench Questions and reference answers used to grade model responses in kensho/VERDICTS. Citation @misc{krumdick2026freelabelslimitationsllmasajudge, title={No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding}, author={Michael Krumdick