Procedural mistake detection on Assembly101-O
78.2Precision
BERT
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2024.04 | 78.2 | 20 | 31.8 | |
2024.04 | 30.7 | 94 | 46.3 | |
2024.04 | 29.2 | 75.8 | 42.1 | |
2024.04 | 27.8 | 84.1 | 41.8 | |
2024.04 | 24.3 | 18.1 | 20.7 | |
2024.04 | 22.1 | 94.2 | 35.8 | |
2024.04 | 16.3 | 30.7 | 21.3 | |
2024.04 | 16.2 | 87.5 | 27.3 |