Binary Classification on Seetrue (test)
83.67Macro F1 ScoreMT-RL-Judge
Evaluation Results
| Method | Links | |
|---|---|---|
| MT-RL-Judgetraining=Multi-task RL2026.03 | 83.67 | |
| RL-Singletraining=Single-task RL2026.03 | 83.41 | |
| SFT-Unifiedtraining=Unified multi-task SFT2026.03 | 82.32 | |
| SFT-Singletraining=Single-task SFT2026.03 | 80.41 | |
| Off-the-shelf2026.03 | 80.01 |