List your company

Mathematical Reasoning on MATH500 (0-shot)

47.4Pass@1HEX
30.7635.0839.443.72Feb 12, 2026

Evaluation results

MethodLinks
HEXGen. Len.=512, Training Necessity=Training-free2026.0247.46,400
DVOTINGGen. Len.=512, Training Necessity=Training-free2026.0245.4701.2
Majority VotingGen. Len.=512, Training Necessity=Training-free2026.02441,280
HEXGen. Len.=256, Training Necessity=Training-free2026.0243.63,200
IGPOGen. Len.=256, Training Necessity=RL2026.0242.8256
d1Gen. Len.=512, Training Necessity=SFT + RL2026.0240.2256
DVOTINGGen. Len.=256, Training Necessity=Training-free2026.0240.2473.7
HEXGen. Len.=128, Training Necessity=Training-free2026.0239.61,600
RFGGen. Len.=256, Training Necessity=FT or RL2026.0239.6512
wd1Gen. Len.=512, Training Necessity=RL2026.0239256
d1Gen. Len.=256, Training Necessity=SFT + RL2026.0238.6128
LLaDA-8B-InstructGen. Len.=512, Training Necessity=Pre-training2026.0238.2512
Majority VotingGen. Len.=256, Training Necessity=Training-free2026.0236.8640
LLaDA-8B-InstructGen. Len.=256, Training Necessity=Pre-training2026.0235256
DVOTINGGen. Len.=128, Training Necessity=Training-free2026.0234.8292.1
wd1Gen. Len.=256, Training Necessity=RL2026.0234.4128
d1Gen. Len.=128, Training Necessity=SFT + RL2026.0233.864
Majority VotingGen. Len.=128, Training Necessity=Training-free2026.0233320
LLaDA-8B-InstructGen. Len.=128, Training Necessity=Pre-training2026.0231.4128