Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

HuggingGPT

Benchmarks

Task NameDataset NameSOTA ResultTrend
Response GenerationHuggingGPT Human Evaluation Set 130 diverse requests (test)
Success Rate63.08
3
Task PlanningHuggingGPT Task Planning (Single Task)
Accuracy52.62
3
Showing 2 of 2 rows