Step-level hallucination detection on ProcessBench
91AUROC
Teacher
Updated 20d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.05 | 91 | |
2026.05 | 75 | |
2026.05 | 67.8 | |
2026.05 | 61.9 | |
2026.05 | 57.1 | |
2026.05 | 51.2 |
Teacher
| Method | Links | |
|---|---|---|
2026.05 | 91 | |
2026.05 | 75 | |
2026.05 | 67.8 | |
2026.05 | 61.9 | |
2026.05 | 57.1 | |
2026.05 | 51.2 |