Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on Math reasoning tasks (Pass@4)
Loading...
67.43
Math Avg. Pass@4 (Before)
AOPD
64.414
65.197
65.98
66.763
May 7, 2026
Math Avg. Pass@4 (Before)
Math Avg. Pass@4 (After)
Math Pass@4 Drop (After - Before)
Updated 26d ago
Evaluation Results
Method
Method
Links
Math Avg. Pass@4 (Before)
Math Avg. Pass@4 (After)
Math Pass@4 Drop (After - Before)
AOPD
SFT warm-up=3K, Contin...
2026.05
67.43
68.04
0.61
GKD
SFT warm-up=3K, Contin...
2026.05
66.96
64.54
-2.42
OPD
SFT warm-up=3K, Contin...
2026.05
66.64
59.15
-7.49
ExOPD
SFT warm-up=3K, Contin...
2026.05
64.53
63.04
-1.49
Feedback
Search any
task
Search any
task
