Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on Brumo 2025 (Pass@1, Efficiency Ratio, MV Budget)
Loading...
96.4
Pass@1
PC-cubic
65.72
73.685
81.65
89.615
May 8, 2026
Pass@1
Token Efficiency Ratio (B_method/BMV)
Standard MV Plateau
Standard MV Budget (BMV)
Updated 23d ago
Evaluation Results
Method
Method
Links
Pass@1
Token Efficiency Ratio (B_method/BMV)
Standard MV Plateau
Standard MV Budget (BMV)
PC-cubic
Model=Nemotron3-30B, T...
2026.05
96.4
-
-
-
Standard MV
Model=Nemotron3-30B, T...
2026.05
89.6
-
-
-
PC-cubic
Model=GPT-OSS-120B, To...
2026.05
85.7
-
-
-
PC-cubic
Model=Nemotron3-30B, T...
2026.05
81.6
0.3
93.2
651
Standard MV
Model=GPT-OSS-120B, To...
2026.05
80.1
-
-
-
PC-cubic
Model=Ministral3-14B,...
2026.05
75.9
-
-
-
AC sweep
Model=GPT-OSS-120B, Ta...
2026.05
71.3
0.2
83.3
3.3
Standard MV
Model=Ministral3-14B,...
2026.05
66.9
-
-
-
Feedback
Search any
task
Search any
task