Qwen/AgentWorldBench download history

Qwen/AgentWorldBench is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 973 times (269 in the last 7 days), and 6,209 times in total. It ranks #19,762 among datasets by monthly downloads.

AgentWorldBench AgentWorldBench is a comprehensive evaluation benchmark for language world models, constructed from real-world observations of frontier model trajectories on established benchmarks such as Tool Decathlon, Terminal-Bench 1.0 & 2.0, and OSWorld-Verified. Every evaluation

Models trained on AgentWorldBench

40 models list it as training data.

Open Qwen/AgentWorldBench on Hugging Face

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