List your company

Code Generation on CRUX

57.2Score (%)INTUITOR
14.61225.668536.72547.7815May 11, 2026May 12, 2026

Evaluation results

MethodLinks
INTUITORBackbone=Qwen2.5-7B, Training Set=MATH2026.0557.2
VIGORBackbone=Qwen2.5-7B, Training Set=MATH2026.0556.38
GT-RewardBackbone=Qwen2.5-7B, Training Set=MATH2026.0555.5
PAPOBase Model=Qwen2.5-14B-Base2026.0548.25
80/20Base Model=Qwen2.5-14B-Base2026.0547.12
DAPOBase Model=Qwen2.5-14B-Base2026.0546.38
Ent-RegBase Model=Qwen2.5-14B-Base2026.0546.25
VIGORBackbone=Qwen2.5-3B, Training Set=MATH2026.0540
INTUITORBackbone=Qwen2.5-3B, Training Set=MATH2026.0538.7
GT-RewardBackbone=Qwen2.5-3B, Training Set=MATH2026.0533
PAPOBase Model=Qwen2.5-7B-Base2026.0530.88
DAPOBase Model=Qwen2.5-7B-Base2026.0530.63
Ent-RegBase Model=Qwen2.5-7B-Base2026.0529.75
80/20Base Model=Qwen2.5-7B-Base2026.0528.62
BaseBase Model=Qwen2.5-14B-Base2026.0528.38
Before RL (Base)Backbone=Qwen2.5-3B, Training Set=MATH2026.0524.38
Before RL (Base)Backbone=Qwen2.5-7B, Training Set=MATH2026.0517.38
BaseBase Model=Qwen2.5-7B-Base2026.0516.25