Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
STEM Reasoning on GaokaoQA
Loading...
41.1
Accuracy
AGPO
37.356
38.328
39.3
40.272
May 20, 2026
Accuracy
Updated 13d ago
Evaluation Results
Method
Method
Links
Accuracy
AGPO
clipping=adaptive, ATS...
2026.05
41.1
AGPO
clipping=adaptive, ATS...
2026.05
40.6
GRPO
clipping=fixed ε
2026.05
39.8
GRPO
ATS=true
2026.05
39.2
Adaptive-KL PPO
2026.05
38.5
PPO
2026.05
37.7
DPO
2026.05
37.5
Feedback
Search any
task
Search any
task
