List your company

Scientific Reasoning on GPQA 0-shot (test)

28.57Pass@1 AccuracydVOTING
22.298823.926925.55527.1831Feb 12, 2026

Evaluation results

MethodLinks
dVOTINGGen. Len.=128, Training Necessity=Training-free, Setting=0-shot2026.0228.57219.3
dVOTINGGen. Len.=256, Training Necessity=Training-free, Setting=0-shot2026.0228.39555.7
HEXGen. Len.=256, Training Necessity=Training-free, Setting=0-shot, reimplementation=true2026.0228.343,200
HEXGen. Len.=128, Training Necessity=Training-free, Setting=0-shot, reimplementation=true2026.0225.671,600
Majority VotingGen. Len.=256, Training Necessity=Training-free, Setting=0-shot2026.0225.45640
LLaDA-8B-InstructGen. Len.=128, Training Necessity=Pre-training, Setting=0-shot2026.0225128
LLaDA-8B-InstructGen. Len.=256, Training Necessity=Pre-training, Setting=0-shot2026.0223.66256
Majority VotingGen. Len.=128, Training Necessity=Training-free, Setting=0-shot2026.0222.54320