Abstention on AbstentionBench UMWP
80.9Abstention F1
GPT-5.2
Updated 8d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 80.9 | 67.9 | 100 | 97.9 | |
2026.05 | 76.7 | 62.3 | 100 | 100 | |
2026.05 | 76.7 | 62.3 | 100 | 95.7 | |
2026.05 | 72.3 | 56.6 | 100 | 95.7 |
GPT-5.2
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 80.9 | 67.9 | 100 | 97.9 | |
2026.05 | 76.7 | 62.3 | 100 | 100 | |
2026.05 | 76.7 | 62.3 | 100 | 95.7 | |
2026.05 | 72.3 | 56.6 | 100 | 95.7 |