List your company

Mathematical Reasoning on GSM8K (Tokens, Pass@5, Cons@5)

456.9Tokens UsedBasel. P^{(0)}_{system}
392.148829.2241,266.31,703.376Apr 22, 2026

Evaluation results

MethodLinks
Basel. P^{(0)}_{system}Model=DS-8B2026.04456.952.3276.389.557.4
Basel. P^{(0)}_{system}Model=DS-14B2026.04470.928.9687.394.971
TRACESModel=DS-14B, Threshold=0.92026.04471.519.9789.194.879.5
TRACESModel=DS-14B, Threshold=0.82026.04485.918.4789.995.181.2
TRACESModel=DS-14B, Threshold=0.72026.04501.716.8290.495.182.6
Basel. P^{(0)}_{user}Model=DS-14B2026.04505.123.885.695.666.2
TRACESModel=DS-8B, Threshold=0.92026.04506.147.1877.593.653.4
Basel. P^{(0)}_{user}Model=DS-8B2026.04525.845.1377.191.757.9
TRACESModel=DS-14B, Threshold=0.62026.04526.514.2390.695.183.2
TRACESModel=DS-8B, Threshold=0.82026.04544.843.1579.293.755.9
TRACESModel=DS-14B, Threshold=0.52026.04553.411.4390.995.184.1
Basel. P^{(1)}_{system}Model=DS-8B2026.04560.841.4875.491.453.7
Basel. P^{(1)}_{system}Model=DS-14B2026.04566.514.5483.895.262.9
TRACESModel=DS-14B, Threshold=0.42026.04567.89.9290.995.184
TRACESModel=DS-8B, Threshold=0.72026.04602.337.1880.493.958.5
StandardModel=DS-14B2026.04662.9—9195.284.3
TRACESModel=DS-8B, Threshold=0.62026.04681.828.8581.594.261.4
TRACESModel=DS-8B, Threshold=0.52026.04761.620.5382.394.263.5
TRACESModel=QwQ-32B, Threshold=0.92026.04777.962.5288.995.976.6
TRACESModel=DS-8B, Threshold=0.42026.04806.815.8182.594.364.1
Basel. P^{(3)}_{system}Model=DS-8B2026.04830.513.3474.890.454.1
Basel. P^{(0)}_{system}Model=QwQ-32B2026.04833.359.859497.486.9
Basel. P^{(3)}_{system}Model=DS-14B2026.04839.6-26.6584.195.263.1
Basel. P^{(1)}_{system}Model=QwQ-32B2026.04871.258.0294.397.587.6
TRACESModel=QwQ-32B, Threshold=0.82026.04895.956.8490.995.980.4
StandardModel=DS-8B2026.04958.3—82.994.365.1
Basel. P^{(0)}_{user}Model=QwQ-32B2026.0498852.495.296.893.7
TRACESModel=QwQ-32B, Threshold=0.72026.041,035.350.1292.596.384.4
TRACESModel=QwQ-32B, Threshold=0.62026.041,270.138.8193.696.387.9
Basel. P^{(3)}_{system}Model=QwQ-32B2026.041,387.333.1693.597.485.5
TRACESModel=QwQ-32B, Threshold=0.52026.041,544.725.5894.696.590.4
TRACESModel=QwQ-32B, Threshold=0.42026.041,685.918.7994.896.691.2
StandardModel=QwQ-32B2026.042,075.7—95.396.593.4