Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Binary Classification on AGIN-Tech (test)
Loading...
81.37
Macro F1 Score
MT-RL-Judge
62.5148
67.4099
72.305
77.2001
Mar 12, 2026
Macro F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Macro F1 Score
MT-RL-Judge
training=Multi-task RL
2026.03
81.37
SFT-Unified
training=Unified multi...
2026.03
81.22
RL-Single
training=Single-task RL
2026.03
80.77
SFT-Single
training=Single-task SFT
2026.03
77.04
Off-the-shelf
2026.03
63.24
Feedback
Search any
task
Search any
task