Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (Out-of-distribution)
Loading...
92
Accuracy
RLTR
88.984
89.767
90.55
91.333
Feb 9, 2026
Accuracy
Maj@4
Maj@16
Maj@64
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
Maj@4
Maj@16
Maj@64
RLTR
Samples for Acc.=64
2026.02
92
93.4
94
94.2
RLVR
Samples for Acc.=64
2026.02
89.4
90.9
92.5
92.9
Base model
Samples for Acc.=64
2026.02
89.1
91.5
92.7
93.3
Feedback
Search any
task
Search any
task