List your company

Tool-use Question Answering on HotpotQA 500 samples (evaluation)

71.6AccuracyBaseline
70.97671.13871.371.462May 13, 2026

Evaluation results

MethodLinks
BaselineModel=openai-realtime-1.52026.0571.64.5—
AsyncIOModel=openai-realtime-1.52026.05713.61.3