List your company

Tool Use on StableToolBench Overall Average

70.3SL (Success Rate)Trace-Based
66.34867.37468.469.426Feb 23, 2026

Evaluation results

MethodLinks
Trace-BasedEvaluation Protocol=Trace-based2026.0270.354.6
Play2PromptEvaluation Protocol=Trace-based2026.0269.852.5
D2Evaluation Protocol=Trace-based2026.0269.552.5
DRAFTEvaluation Protocol=Trace-based2026.0268.150
D0Evaluation Protocol=Trace-based2026.0267.348
D1Evaluation Protocol=Trace-based2026.0266.549.4