benchflow/ClawsBench download history
benchflow/ClawsBench is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 485 times (147 in the last 7 days), and 3,201 times in total. It ranks #33,942 among datasets by monthly downloads.
ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces Overview ClawsBench evaluates LLM agents on realistic productivity tasks across 5 high-fidelity mock services (Gmail, Calendar, Docs, Drive, Slack), measuring both capability