NeuralMetrics/ProcessBench download history

NeuralMetrics/ProcessBench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 20 times (13 in the last 7 days), and 101 times in total. It ranks #374,093 among datasets by monthly downloads.

Neural Metrics · Step-level evaluation, because extraction is a chain. Document extraction is a multi-step process, and an end-to-end accuracy number hides where it broke. ProcessBench evaluates reasoning step by step, which is the shape of evaluation we want for our own pipeli

Open NeuralMetrics/ProcessBench on Hugging Face

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