Share your thoughts, 1 month free Claude Pro on usSee more

Mathematical Reasoning on FrontierScience-Olympiad

50.8Accuracy

PC-cubic

Updated 23d ago

Evaluation Results

Method	Links
PC-cubic 2026.05		50.8
PC-cubic 2026.05		50.7
PC-cubic 2026.05		50.6
PC-quadratic 2026.05		50.4
PC-quadratic 2026.05		50.4
PC-quadratic 2026.05		50.3
PC-cubic 2026.05		50.3
PC-quadratic 2026.05		50.2
P(True) 2026.05		50
P(True) 2026.05		50
Standard MV 2026.05		49.9
Self-certainty 2026.05		49.7
DeepConf tail 2026.05		49.7
PC-linear 2026.05		49.6
PC-linear 2026.05		49.6
Standard MV 2026.05		49.5
Self-certainty 2026.05		49.5
DeepConf tail 2026.05		49.5
PC-linear 2026.05		49.5
Self-certainty 2026.05		49.4
DeepConf tail 2026.05		49.4
PC-linear 2026.05		49.4
Standard MV 2026.05		49.3
DeepConf tail 2026.05		49.3
P(True) 2026.05		49.3
P(True) 2026.05		49.2
Self-certainty 2026.05		49.1
Standard MV 2026.05		49
PC-quadratic 2026.05		48.6
PC-cubic 2026.05		48.6
PC-linear 2026.05		48.1
DeepConf tail 2026.05		47
Standard MV 2026.05		46.8
Self-certainty 2026.05		46.8
P(True) 2026.05		46.5
PC-quadratic 2026.05		43.3
PC-cubic 2026.05		43.3
PC-linear 2026.05		42.9
DeepConf tail 2026.05		40.5
Standard MV 2026.05		40.4
Self-certainty 2026.05		40.2
P(True) 2026.05		39.4
PC-cubic 2026.05		18.1
PC-cubic 2026.05		17.4
PC-quadratic 2026.05		17.3
PC-quadratic 2026.05		17
PC-linear 2026.05		16.2
PC-linear 2026.05		16
PC-cubic 2026.05		15.8
PC-quadratic 2026.05		15.6
PC-linear 2026.05		14.9
P(True) 2026.05		14.6
P(True) 2026.05		14.3
Standard MV 2026.05		14.2
Standard MV 2026.05		14.1
Standard MV 2026.05		13.7
Self-certainty 2026.05		13.7
DeepConf tail 2026.05		13.7
P(True) 2026.05		13.7
Self-certainty 2026.05		13.5
DeepConf tail 2026.05		13.4
Self-certainty 2026.05		13
DeepConf tail 2026.05		13