Mathematical Reasoning on Brumo 2025 (Pass@1, Efficiency Ratio, MV Budget)
96.4Pass@1PC-cubic
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| PC-cubicModel=Nemotron3-30B, Token Budget (B)=5M2026.05 | 96.4 | — | — | — | |
| Standard MVModel=Nemotron3-30B, Token Budget (B)=250k2026.05 | 89.6 | — | — | — | |
| PC-cubicModel=GPT-OSS-120B, Token Budget (B)=5M2026.05 | 85.7 | — | — | — | |
| PC-cubicModel=Nemotron3-30B, Target accuracy (alpha)=90%2026.05 | 81.6 | 0.3 | 93.2 | 651 | |
| Standard MVModel=GPT-OSS-120B, Token Budget (B)=250k2026.05 | 80.1 | — | — | — | |
| PC-cubicModel=Ministral3-14B, Token Budget (B)=5M2026.05 | 75.9 | — | — | — | |
| AC sweepModel=GPT-OSS-120B, Target accuracy (alpha)=99%2026.05 | 71.3 | 0.2 | 83.3 | 3.3 | |
| Standard MVModel=Ministral3-14B, Token Budget (B)=250k2026.05 | 66.9 | — | — | — |