Planning and Tool Use on SLATE synthetic
36.4Tool Match Rate
EGB-Logits
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 36.4 | 67.8 | 85.1 | |
2026.04 | 33.6 | 51.3 | 83 | |
2026.04 | 30 | 29.3 | 78.2 | |
2026.04 | 25.2 | 44.2 | 82.9 | |
2026.04 | 23.2 | - | - |
EGB-Logits
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 36.4 | 67.8 | 85.1 | |
2026.04 | 33.6 | 51.3 | 83 | |
2026.04 | 30 | 29.3 | 78.2 | |
2026.04 | 25.2 | 44.2 | 82.9 | |
2026.04 | 23.2 | - | - |