Tool Use on StableToolBench v1 (test)
75.5G1 Category SLD1
Evaluation Results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| D1trace-free=true2026.02 | 75.5 | 64.9 | 74.7 | 66.1 | 68 | 53.7 | 67.9 | 43.1 | 67.4 | 42.9 | 45.2 | 25.4 | 66.5 | 49.4 | |
| Trace-Free+trace-free=true2026.02 | 73.8 | 65.6 | 72.6 | 60 | 70 | 56.4 | 68.7 | 47.5 | 71.4 | 48.3 | 63.9 | 46.4 | 70.1 | 54 | |
| D0trace-free=true2026.02 | 73 | 62.4 | 72.8 | 62.3 | 71 | 52.8 | 68.4 | 42.4 | 67.8 | 43.4 | 50.7 | 24.6 | 67.3 | 48 | |
| Trace-Freetrace-free=true2026.02 | 71.8 | 62.7 | 70.8 | 60.8 | 68.5 | 53.6 | 66.4 | 44.1 | 69.2 | 46.4 | 59.9 | 41.8 | 67.8 | 51.6 | |
| EasyTooltrace-free=true2026.02 | 67.4 | 56.9 | 69.5 | 56 | 66.4 | 47.6 | 68.1 | 40.4 | 68.2 | 43.5 | 41.4 | 17.5 | 63.5 | 43.7 |