Step-level hallucination detection on PRM800K
99.8AUROC
Student
Updated 20d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.05 | 99.8 | |
2026.05 | 98.5 | |
2026.05 | 91.3 | |
2026.05 | 54.5 | |
2026.05 | 48 | |
2026.05 | 45.8 |
Student
| Method | Links | |
|---|---|---|
2026.05 | 99.8 | |
2026.05 | 98.5 | |
2026.05 | 91.3 | |
2026.05 | 54.5 | |
2026.05 | 48 | |
2026.05 | 45.8 |