List your company

Mathematical Reasoning on AIME 23-24

1,986.5Token CountTRACES
1,542.1084,541.7547,541.410,541.046Apr 22, 2026

Evaluation results

MethodLinks
TRACESthreshold=0.9, Backbone=DS-Qwen14B, Seed=422026.041,986.50.0584.83
TRACESthreshold=0.8, Backbone=DS-Qwen14B, Seed=422026.044,015.30.13369.34
TRACESthreshold=0.7, Backbone=DS-Qwen14B, Seed=422026.045,949.50.254.57
TRACESthreshold=0.6, Backbone=DS-Qwen14B, Seed=422026.047,983.70.339.04
TRACESthreshold=0.5, Backbone=DS-Qwen14B, Seed=422026.049,478.90.38327.62
Basel. P^{(1)}_{system}Backbone=DS-Qwen14B, Seed=422026.0410,181.20.51722.26
TRACESthreshold=0.4, Backbone=DS-Qwen14B, Seed=422026.0410,524.30.41719.64
Basel. P^{(0)}_{system}Backbone=DS-Qwen14B, Seed=422026.0411,095.90.515.27
Basel. P^{(3)}_{system}Backbone=DS-Qwen14B, Seed=422026.0411,635.70.46711.15
Basel. P^{(0)}_{user}Backbone=DS-Qwen14B, Seed=422026.0412,748.40.4222.66
StandardBackbone=DS-Qwen14B, Seed=422026.0413,096.30.483—