List your company

Mathematical Reasoning on MATH 500 (Accuracy, log C)

54.4AccuracyBoBN
8.43220.36632.344.234Jul 3, 2026

Evaluation results

MethodLinks
BoBNN=16, Backbone=tulu3-8b2026.0754.4—
pi_refN=16, Backbone=tulu3-8b2026.0753.8—
URIALN=16, Backbone=tulu3-8b2026.0752—
BoBNN=4, Backbone=tulu3-8b2026.0749.60.55
BoBNN=1, Backbone=tulu3-8b2026.0746.60.55
pi_refN=1, Backbone=tulu3-8b2026.0745.60.58
URIALN=1, Backbone=tulu3-8b2026.07420.55
BoBNN=16, Backbone=zephyr-7b2026.0721—
pi_refN=16, Backbone=zephyr-7b2026.0717.4—
BoBNN=4, Backbone=zephyr-7b2026.0715.2—
URIALN=16, Backbone=zephyr-7b2026.0715—
BoBNN=1, Backbone=zephyr-7b2026.0713.80.63
URIALN=1, Backbone=zephyr-7b2026.0712.20.66
pi_refN=1, Backbone=zephyr-7b2026.0710.20.67