yale-nlp/physics-verified-model-outputs download history

yale-nlp/physics-verified-model-outputs is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 442 times (318 in the last 7 days), and 442 times in total. It ranks #36,485 among datasets by monthly downloads.

PHYSICS-Verified model outputs The raw responses and judge verdicts behind the results of PHYSICS-Verified: 53 models, one sample per problem, and one verdict per reference answer from an LLM judge. The harness is yale-nlp/physics-verified. Canary — BENCHMARK DATA SHOULD NEVER APPEAR

Open yale-nlp/physics-verified-model-outputs on Hugging Face