List your company

Binary Classification on AGIN-Tech (test)

81.37Macro F1 ScoreMT-RL-Judge
62.514867.409972.30577.2001Mar 12, 2026

Evaluation results

MethodLinks
MT-RL-Judgetraining=Multi-task RL2026.0381.37
SFT-Unifiedtraining=Unified multi-task SFT2026.0381.22
RL-Singletraining=Single-task RL2026.0380.77
SFT-Singletraining=Single-task SFT2026.0377.04
Off-the-shelf2026.0363.24