Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Problem Solving on MATH 500 (test)
Loading...
83.6
Average@16 Acc
PRM-CoT (Process-Aware)
77.984
79.442
80.9
82.358
Dec 2, 2025
Average@16 Acc
Pass@1 Acc
Pass@8 Acc
Pass@16 Acc
Updated 4d ago
Evaluation Results
Method
Method
Links
Average@16 Acc
Pass@1 Acc
Pass@8 Acc
Pass@16 Acc
PRM-CoT (Process-Aware)
Base Policy=Qwen2.5-Ma...
2025.12
83.6
85.4
91
92.2
RLVR (Ground Truth)
Base Policy=Qwen2.5-Ma...
2025.12
82.5
83.7
91
92
PRM (Process-Aware)
Base Policy=Qwen2.5-Ma...
2025.12
81.43
82.8
90.8
91.4
SFT (Baseline)
Base Policy=Qwen2.5-Ma...
2025.12
78.2
79
84.8
88.6
Feedback
Search any
task
Search any
task