List your company

Mathematical Reasoning on GSM8K (0-shot)

88.78Pass@1HEX
69.85274.76679.6884.594Feb 12, 2026

Evaluation results

MethodLinks
HEXGen. Len.=512, Training Necessity=Training-free2026.0288.786,400
DVOTINGGen. Len.=512, Training Necessity=Training-free2026.0287.72289.6
Majority VotingGen. Len.=512, Training Necessity=Training-free2026.0286.281,280
HEXGen. Len.=256, Training Necessity=Training-free2026.0285.753,200
DVOTINGGen. Len.=256, Training Necessity=Training-free2026.0283.78237.1
IGPOGen. Len.=256, Training Necessity=RL2026.0283.6256
Majority VotingGen. Len.=256, Training Necessity=Training-free2026.0282.33640
wd1Gen. Len.=512, Training Necessity=RL2026.0282.3256
d1Gen. Len.=512, Training Necessity=SFT + RL2026.0282.1256
LLaDA-8B-InstructGen. Len.=512, Training Necessity=Pre-training2026.0281.5512
RFGGen. Len.=256, Training Necessity=FT or RL2026.0281.3512
d1Gen. Len.=256, Training Necessity=SFT + RL2026.0281.1128
wd1Gen. Len.=256, Training Necessity=RL2026.0280.8128
HEXGen. Len.=128, Training Necessity=Training-free2026.0280.141,600
DVOTINGGen. Len.=128, Training Necessity=Training-free2026.0278.24170.4
LLaDA-8B-InstructGen. Len.=256, Training Necessity=Pre-training2026.0276.72256
Majority VotingGen. Len.=128, Training Necessity=Training-free2026.0276.72320
d1Gen. Len.=128, Training Necessity=SFT + RL2026.0273.264
LLaDA-8B-InstructGen. Len.=128, Training Necessity=Pre-training2026.0270.58128