List your company

Mathematical Reasoning on FrontierScience-Olympiad

50.8AccuracyPC-cubic
11.48821.69431.942.106May 8, 2026

Evaluation results

MethodLinks
PC-cubicModel=GPT-OSS-120B, Token Budget (B)=1M2026.0550.8
PC-cubicModel=GPT-OSS-120B, Token Budget (B)=5M2026.0550.7
PC-cubicModel=GPT-OSS-120B, Token Budget (B)=250k2026.0550.6
PC-quadraticModel=GPT-OSS-120B, Token Budget (B)=1M2026.0550.4
PC-quadraticModel=Nemotron3-30B, Token Budget (B)=5M2026.0550.4
PC-quadraticModel=GPT-OSS-120B, Token Budget (B)=5M2026.0550.3
PC-cubicModel=Nemotron3-30B, Token Budget (B)=5M2026.0550.3
PC-quadraticModel=GPT-OSS-120B, Token Budget (B)=250k2026.0550.2
P(True)Model=GPT-OSS-120B, Token Budget (B)=1M2026.0550
P(True)Model=GPT-OSS-120B, Token Budget (B)=5M2026.0550
Standard MVModel=GPT-OSS-120B, Token Budget (B)=5M2026.0549.9
Self-certaintyModel=GPT-OSS-120B, Token Budget (B)=5M2026.0549.7
DeepConf tailModel=GPT-OSS-120B, Token Budget (B)=5M2026.0549.7
PC-linearModel=GPT-OSS-120B, Token Budget (B)=1M2026.0549.6
PC-linearModel=GPT-OSS-120B, Token Budget (B)=5M2026.0549.6
Standard MVModel=GPT-OSS-120B, Token Budget (B)=1M2026.0549.5
Self-certaintyModel=GPT-OSS-120B, Token Budget (B)=1M2026.0549.5
DeepConf tailModel=GPT-OSS-120B, Token Budget (B)=1M2026.0549.5
PC-linearModel=GPT-OSS-120B, Token Budget (B)=250k2026.0549.5
Self-certaintyModel=GPT-OSS-120B, Token Budget (B)=250k2026.0549.4
DeepConf tailModel=Nemotron3-30B, Token Budget (B)=5M2026.0549.4
PC-linearModel=Nemotron3-30B, Token Budget (B)=5M2026.0549.4
Standard MVModel=GPT-OSS-120B, Token Budget (B)=250k2026.0549.3
DeepConf tailModel=GPT-OSS-120B, Token Budget (B)=250k2026.0549.3
P(True)Model=GPT-OSS-120B, Token Budget (B)=250k2026.0549.3
P(True)Model=Nemotron3-30B, Token Budget (B)=5M2026.0549.2
Self-certaintyModel=Nemotron3-30B, Token Budget (B)=5M2026.0549.1
Standard MVModel=Nemotron3-30B, Token Budget (B)=5M2026.0549
PC-quadraticModel=Nemotron3-30B, Token Budget (B)=1M2026.0548.6
PC-cubicModel=Nemotron3-30B, Token Budget (B)=1M2026.0548.6
PC-linearModel=Nemotron3-30B, Token Budget (B)=1M2026.0548.1
DeepConf tailModel=Nemotron3-30B, Token Budget (B)=1M2026.0547
Standard MVModel=Nemotron3-30B, Token Budget (B)=1M2026.0546.8
Self-certaintyModel=Nemotron3-30B, Token Budget (B)=1M2026.0546.8
P(True)Model=Nemotron3-30B, Token Budget (B)=1M2026.0546.5
PC-quadraticModel=Nemotron3-30B, Token Budget (B)=250k2026.0543.3
PC-cubicModel=Nemotron3-30B, Token Budget (B)=250k2026.0543.3
PC-linearModel=Nemotron3-30B, Token Budget (B)=250k2026.0542.9
DeepConf tailModel=Nemotron3-30B, Token Budget (B)=250k2026.0540.5
Standard MVModel=Nemotron3-30B, Token Budget (B)=250k2026.0540.4
Self-certaintyModel=Nemotron3-30B, Token Budget (B)=250k2026.0540.2
P(True)Model=Nemotron3-30B, Token Budget (B)=250k2026.0539.4
PC-cubicModel=Ministral3-14B, Token Budget (B)=5M2026.0518.1
PC-cubicModel=Ministral3-14B, Token Budget (B)=1M2026.0517.4
PC-quadraticModel=Ministral3-14B, Token Budget (B)=5M2026.0517.3
PC-quadraticModel=Ministral3-14B, Token Budget (B)=1M2026.0517
PC-linearModel=Ministral3-14B, Token Budget (B)=5M2026.0516.2
PC-linearModel=Ministral3-14B, Token Budget (B)=1M2026.0516
PC-cubicModel=Ministral3-14B, Token Budget (B)=250k2026.0515.8
PC-quadraticModel=Ministral3-14B, Token Budget (B)=250k2026.0515.6
PC-linearModel=Ministral3-14B, Token Budget (B)=250k2026.0514.9
P(True)Model=Ministral3-14B, Token Budget (B)=5M2026.0514.6
P(True)Model=Ministral3-14B, Token Budget (B)=1M2026.0514.3
Standard MVModel=Ministral3-14B, Token Budget (B)=5M2026.0514.2
Standard MVModel=Ministral3-14B, Token Budget (B)=1M2026.0514.1
Standard MVModel=Ministral3-14B, Token Budget (B)=250k2026.0513.7
Self-certaintyModel=Ministral3-14B, Token Budget (B)=5M2026.0513.7
DeepConf tailModel=Ministral3-14B, Token Budget (B)=5M2026.0513.7
P(True)Model=Ministral3-14B, Token Budget (B)=250k2026.0513.7
Self-certaintyModel=Ministral3-14B, Token Budget (B)=1M2026.0513.5
DeepConf tailModel=Ministral3-14B, Token Budget (B)=1M2026.0513.4
Self-certaintyModel=Ministral3-14B, Token Budget (B)=250k2026.0513
DeepConf tailModel=Ministral3-14B, Token Budget (B)=250k2026.0513