List your company

Quantitative Reasoning on AIME

28.7AccuracyGround Truth
3.29289.888916.48523.0811May 31, 2026

Evaluation results

MethodLinks
Ground TruthTeacher=Qwen3-4B, Student=Qwen3-8B2026.0528.7—
Ground TruthTeacher=Qwen3-8B, Student=Qwen3-8B2026.0528.4—
NTFTeacher=Qwen3-4B, Student=Qwen3-8B2026.0527.991.7
NTFTeacher=Qwen3-8B, Student=Qwen3-8B2026.0527.489.2
Ground TruthTeacher=Qwen3-1.7B, Student=Qwen3-8B2026.0527.4—
I-ConfidenceTeacher=Qwen3-8B, Student=Qwen3-8B2026.0527.388.4
NaiveTeacher=Qwen3-4B, Student=Qwen3-8B2026.0527.284.7
V-ConfidenceTeacher=Qwen3-4B, Student=Qwen3-8B2026.0527.183.7
NaiveTeacher=Qwen3-8B, Student=Qwen3-8B2026.0526.883.2
I-ConfidenceTeacher=Qwen3-4B, Student=Qwen3-8B2026.0526.779.6
NTFTeacher=Qwen3-1.7B, Student=Qwen3-8B2026.0526.691
V-ConfidenceTeacher=Qwen3-8B, Student=Qwen3-8B2026.0526.580
NaiveTeacher=Qwen3-1.7B, Student=Qwen3-8B2026.052683.5
V-ConfidenceTeacher=Qwen3-1.7B, Student=Qwen3-8B2026.0525.982.4
I-ConfidenceTeacher=Qwen3-1.7B, Student=Qwen3-8B2026.0525.678.8
Ground TruthTeacher=Qwen3-1.7B, Student=Qwen3-4B2026.0522.9—
NTFTeacher=Qwen3-1.7B, Student=Qwen3-4B2026.052292.5
I-ConfidenceTeacher=Qwen3-1.7B, Student=Qwen3-4B2026.0520.781.7
NaiveTeacher=Qwen3-1.7B, Student=Qwen3-4B2026.0519.672.5
No-GRPOTeacher=Qwen3-1.7B, Student=Qwen3-8B2026.0518.9—
No-GRPOTeacher=Qwen3-4B, Student=Qwen3-8B2026.0518.9—
No-GRPOTeacher=Qwen3-8B, Student=Qwen3-8B2026.0518.9—
Teacher PerformanceTeacher=Qwen3-8B, Student=Qwen3-8B2026.0518.88—
V-ConfidenceTeacher=Qwen3-1.7B, Student=Qwen3-4B2026.0518.765
Teacher PerformanceTeacher=Qwen3-4B, Student=Qwen3-8B2026.0510.91—
No-GRPOTeacher=Qwen3-1.7B, Student=Qwen3-4B2026.0510.9—
Teacher PerformanceTeacher=Qwen3-1.7B, Student=Qwen3-4B2026.054.27—
Teacher PerformanceTeacher=Qwen3-1.7B, Student=Qwen3-8B2026.054.27—