Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Graduate-level Reasoning Evaluation on GPQA (Utility)
Loading...
50
Utility
Base
47.3688
48.0519
48.735
49.4181
Jun 24, 2026
Utility
Updated 1mo ago
Evaluation Results
Method
Method
Links
Utility
Base
Backbone=Qwen3-4B
2026.06
50
PolicyAlign
Backbone=Qwen3-4B
2026.06
47.98
ICL
Backbone=Qwen3-4B
2026.06
47.47
SFT
Backbone=Qwen3-4B
2026.06
47.47
Feedback
Search any
task
Search any
task