List your company

Mathematical Reasoning on Aggregate (GSM8K, MATH, DAPO-MATH, AMC23, AIME25)

76.6Average Pass@1Qwen3-4B
45.453.561.669.7May 16, 2026

Evaluation results

MethodLinks
Qwen3-4BTraining Set=DAPO-MATH, Method Variant=LZE, FLOPs Budget=5.48 × 10^192026.0576.6
Qwen3-4BTraining Set=DAPO-MATH, Method Variant=Base, FLOPs Budget=8.56 × 10^192026.0576.4
Qwen3-8BTraining Set=DAPO-MATH, Method Variant=LZE, FLOPs Budget=6.30 × 10^192026.0575.5
Qwen3-4BTraining Set=MATH, Method Variant=LZE, FLOPs Budget=7.55 × 10^192026.0575
Qwen3-4BTraining Set=MATH, Method Variant=Base, FLOPs Budget=1.18 × 10^202026.0574.2
Qwen3-8BTraining Set=DAPO-MATH, Method Variant=Base, FLOPs Budget=9.85 × 10^192026.0571.6
Qwen2.5-Math-7BTraining Set=DAPO-MATH, Method Variant=LZE, FLOPs Budget=1.89 × 10^202026.0567.3
Qwen2.5-Math-7BTraining Set=DAPO-MATH, Method Variant=Base, FLOPs Budget=2.94 × 10^202026.0565.5
Qwen2.5-Math-7BTraining Set=MATH, Method Variant=LZE, FLOPs Budget=1.09 × 10^202026.0560
Qwen3-1.7BTraining Set=GSM8K, Method Variant=LZE, FLOPs Budget=3.17 × 10^192026.0558.2
Qwen2.5-Math-7BTraining Set=MATH, Method Variant=Base, FLOPs Budget=1.70 × 10^202026.0558.1
Qwen3-1.7BTraining Set=GSM8K, Method Variant=Base, FLOPs Budget=4.94 × 10^192026.0554.8
Qwen2.5-Math-1.5BTraining Set=MATH, Method Variant=LZE, FLOPs Budget=3.73 × 10^192026.0550.9
Qwen2.5-Math-1.5BTraining Set=GSM8K, Method Variant=LZE, FLOPs Budget=3.50 × 10^192026.0548
Qwen2.5-Math-1.5BTraining Set=MATH, Method Variant=Base, FLOPs Budget=5.82 × 10^192026.0546.9
Qwen2.5-Math-1.5BTraining Set=GSM8K, Method Variant=Base, FLOPs Budget=5.47 × 10^192026.0546.6