Tool Use on StableToolBench G1 Category
76.8SLTrace-Based
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Trace-BasedEvaluation Protocol=Trace-based2026.02 | 76.8 | 64.5 | |
| D2Evaluation Protocol=Trace-based2026.02 | 75.9 | 66.4 | |
| D1Evaluation Protocol=Trace-based2026.02 | 75.5 | 64.9 | |
| Play2PromptEvaluation Protocol=Trace-based2026.02 | 74.6 | 66.2 | |
| DRAFTEvaluation Protocol=Trace-based2026.02 | 73.2 | 60.4 | |
| D0Evaluation Protocol=Trace-based2026.02 | 73 | 62.4 | |
| Play2PromptEvaluation Protocol=Trace-based2026.02 | 71.3 | 55.2 | |
| D2Evaluation Protocol=Trace-based2026.02 | 71.1 | 57.3 | |
| D0Evaluation Protocol=Trace-based2026.02 | 71 | 52.8 | |
| Trace-BasedEvaluation Protocol=Trace-based2026.02 | 69.1 | 54.7 | |
| D1Evaluation Protocol=Trace-based2026.02 | 68 | 53.7 | |
| DRAFTEvaluation Protocol=Trace-based2026.02 | 67.8 | 48.5 |