Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Binary Classification on ImageReward (test)
Loading...
65.07
Macro-F1
RL-Single
54.67
57.37
60.07
62.77
Mar 12, 2026
Macro-F1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Macro-F1
RL-Single
training=Single-task RL
2026.03
65.07
MT-RL-Judge
training=Multi-task RL
2026.03
64.97
SFT-Single
training=Single-task SFT
2026.03
64.95
SFT-Unified
training=Unified multi...
2026.03
63.34
Off-the-shelf
2026.03
55.07
Feedback
Search any
task
Search any
task