amazon/sop-bench download history
amazon/sop-bench is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 672 times (260 in the last 7 days), and 1,698 times in total. It ranks #26,206 among datasets by monthly downloads.
SOP-Bench: Complex Industrial SOPs for Evaluating LLM Agents 馃搫 Paper: SOP-Bench: Complex Industrial SOPs for Evaluating LLM Agents 馃彮 Human Expert-Authored SOPs 路 馃 Human-AI Collaborative Framework 路 馃搳 Executable Interfaces 路 馃敡 Two Agent Architectures 路 馃搱 11 Frontier Models Evaluated