Share your thoughts, 1 month free Claude Pro on usSee more

Binary Classification on Seetrue (test)

83.67Macro F1 Score

MT-RL-Judge

Updated 1mo ago

Evaluation Results

Method	Links
MT-RL-Judge 2026.03		83.67
RL-Single 2026.03		83.41
SFT-Unified 2026.03		82.32
SFT-Single 2026.03		80.41
Off-the-shelf 2026.03		80.01