Tool Use on StableToolBench G2 Instruction
68.8SL Score
Trace-Based
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 68.8 | 45.4 | |
2026.02 | 68.2 | 43.2 | |
2026.02 | 68.2 | 44.9 | |
2026.02 | 68 | 43.4 | |
2026.02 | 67.8 | 43.4 | |
2026.02 | 67.4 | 42.9 |
Trace-Based
| Method | Links | ||
|---|---|---|---|
2026.02 | 68.8 | 45.4 | |
2026.02 | 68.2 | 43.2 | |
2026.02 | 68.2 | 44.9 | |
2026.02 | 68 | 43.4 | |
2026.02 | 67.8 | 43.4 | |
2026.02 | 67.4 | 42.9 |