Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Problem Solving on MATH (pass@50)
Loading...
90
pass@50
GPT-4o-mini
71.072
75.986
80.9
85.814
Oct 4, 2025
pass@50
Diversity
Updated 4d ago
Evaluation Results
Method
Method
Links
pass@50
Diversity
GPT-4o-mini
Sampling Strategy=GUID...
2025.10
90
5
GPT-4o-mini
Sampling Strategy=Repe...
2025.10
85.71
3.2
Phi-4-mini-instruct
Sampling Strategy=GUID...
2025.10
80.8
3.4
Phi-4-mini-instruct
Sampling Strategy=Repe...
2025.10
71.8
2.1
Feedback
Search any
task
Search any
task