Hugging Face
Hugging Face’s XYBench Tests Whether Models Can Actually Get Things Done
Hugging Face and Ai2's XYBench tests whether models can understand real-world needs, use tools and complete tasks—not merely answer questions.
1 article tagged with this topic
Hugging Face and Ai2's XYBench tests whether models can understand real-world needs, use tools and complete tasks—not merely answer questions.