hsiung/MagicBench download history

hsiung/MagicBench is a question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 28 times (6 in the last 7 days), and 517 times in total. It ranks #289,747 among datasets by monthly downloads.

MagicBench: A Deception-Sensitive Cognitive Benchmark for LLMs Project page | Code | Dataset MagicBench is a deception-sensitive cognitive benchmark for language models built around magic-trick understanding. Rather than testing recall alone, it probes whether a model can reason about hid

Open hsiung/MagicBench on Hugging Face

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