Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Problem Solving on AMC'23 (test)
Loading...
62.17
Avg Acc @16
PRM-CoT (Process-Aware)
47.4332
51.2591
55.085
58.9109
Dec 2, 2025
Avg Acc @16
Pass@1 Acc
Pass@8 Acc
Pass@16 Acc
Updated 4d ago
Evaluation Results
Method
Method
Links
Avg Acc @16
Pass@1 Acc
Pass@8 Acc
Pass@16 Acc
PRM-CoT (Process-Aware)
Base Policy=Qwen2.5-Ma...
2025.12
62.17
66.3
75.3
79.8
PRM (Process-Aware)
Base Policy=Qwen2.5-Ma...
2025.12
58.75
62.5
71.08
75.9
RLVR (Ground Truth)
Base Policy=Qwen2.5-Ma...
2025.12
56.3
59.1
69.88
74.7
SFT (Baseline)
Base Policy=Qwen2.5-Ma...
2025.12
48
52.5
57.83
66.27
Feedback
Search any
task
Search any
task