List your company

Mathematical Reasoning on AIME 25 (Avg@32, Pass@8, Dist-N, SemDiv)

86.67Pass@8Qwen-3-4B
-0.003622.49824567.5018Jan 30, 2026Jan 31, 2026Feb 1, 2026Feb 3, 2026Feb 4, 2026Feb 5, 2026Feb 7, 2026

Evaluation results

MethodLinks
Qwen-3-4BAttention=Full attention2026.0286.67———
Qwen-3-8BAttention=Full attention2026.0283.33———
ParisKVBackbone=Qwen-3-4B2026.0280———
ParisKVBackbone=Qwen-3-8B2026.0273.33———
CraEGTemperature=0.7, Top-p=0.95, Backbone=Qwen3-1.7B2026.0160.3737.2944.4614.5
CraEGTemperature=1, Top-p=1, Backbone=Qwen3-1.7B2026.0158.9136.4652.0317.7
Standard SamplingTemperature=0.7, Top-p=0.95, Backbone=Qwen3-1.7B2026.0158.6935.7343.1814.71
Standard SamplingTemperature=1, Top-p=1, Backbone=Qwen3-1.7B2026.0157.3335.9450.3616.61
ParisKVBackbone=DS-R1-Llam-8B2026.0253.3———
DS-R1-Llam-8BAttention=Full attention2026.0250———
PQCacheBackbone=Qwen-3-8B2026.0216.67———
PQCacheBackbone=DS-R1-Llam-8B2026.0213.3———
MagicPIGBackbone=DS-R1-Llam-8B2026.0213.3———
MagicPIGBackbone=Qwen-3-8B2026.0210———
MagicPIGBackbone=Qwen-3-4B2026.026.67———
PQCacheBackbone=Qwen-3-4B2026.023.33———
HPDModel Family=Qwen 2.5, Student Model=1.5B2026.04—9.89——
HPDModel Family=Qwen 2.5, Student Model=3B2026.04—18.13——
HPDModel Family=LLaMA 3, Student Model=1B2026.04—2.08——
HPDModel Family=LLaMA 3, Student Model=3B2026.04—12.71——
MSModel Family=Qwen 2.5, Student Model=1.5B2026.04—1.04——
MSModel Family=Qwen 2.5, Student Model=3B2026.04—2.5——
MTModel Family=Qwen 2.5, Model Size=7B, Role=Teacher2026.04—27.19——
MTModel Family=LLaMA 3, Model Size=8B, Role=Teacher2026.04—18.02——