Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on HMMT 2025 (test)
Loading...
93.3
Accuracy
RSA
89.556
90.528
91.5
92.472
Apr 9, 2026
Accuracy
Cost per Problem ($)
Cost Savings Multiplier
Updated 9d ago
Evaluation Results
Method
Method
Links
Accuracy
Cost per Problem ($)
Cost Savings Multiplier
RSA
Model 2=GPT-5 mini, Pa...
2026.04
93.3
0.94
1
SQUEEZE EVOLVE
Model 1=GPT-OSS-20B, M...
2026.04
93.1
0.56
1.7
SQUEEZE EVOLVE
Model 1=GPT-OSS-20B, M...
2026.04
92
0.25
1.6
RSA
Model 2=GPT-OSS-120B,...
2026.04
89.7
0.41
1
Feedback
Search any
task
Search any
task