metr-evals/malt-public download history

metr-evals/malt-public is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 417 times (75 in the last 7 days), and 2,585 times in total. It ranks #38,171 among datasets by monthly downloads.

MALT: Manually-Reviewed Agentic Labeled Transcripts MALT-public is our collection of agent transcripts. Our public variant only includes data on non-internal tasks, which includes 30 task families and 169 tasks, across ~19 different models (some might be different releases of the same mod

Open metr-evals/malt-public on Hugging Face

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