Social Reasoning on When2Call
54.5Accuracy
AutoAdapt
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.03 | 54.5 | |
2026.03 | 50 | |
2026.03 | 48.1 | |
2026.03 | 46.9 | |
2026.03 | 45.4 |
AutoAdapt
| Method | Links | |
|---|---|---|
2026.03 | 54.5 | |
2026.03 | 50 | |
2026.03 | 48.1 | |
2026.03 | 46.9 | |
2026.03 | 45.4 |