Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General knowledge evaluation on MMLU Pro
Loading...
68.41
Utility Score
ICL
65.7788
66.4619
67.145
67.8281
Jun 24, 2026
Utility Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Utility Score
ICL
Backbone=Qwen3-4B
2026.06
68.41
PolicyAlign
Backbone=Qwen3-4B
2026.06
68.29
Base
Backbone=Qwen3-4B
2026.06
66.29
SFT
Backbone=Qwen3-4B
2026.06
65.88
Feedback
Search any
task
Search any
task
