List your company

Binary Classification on Seetrue (test)

83.67Macro F1 ScoreMT-RL-Judge
79.863680.851881.8482.8282Mar 12, 2026

Evaluation results

MethodLinks
MT-RL-Judgetraining=Multi-task RL2026.0383.67
RL-Singletraining=Single-task RL2026.0383.41
SFT-Unifiedtraining=Unified multi-task SFT2026.0382.32
SFT-Singletraining=Single-task SFT2026.0380.41
Off-the-shelf2026.0380.01