List your company

Mathematical Reasoning on GSM8K 8B Instruct (test)

58.6AccuracyProb Margin + Both
41.4445.89550.3554.805Apr 12, 2026

Evaluation results

MethodLinks
Prob Margin + BothToken Selection (T.S.)=-, Position Selection (P.S.)=L&E, Randomness Step=all, Compute Budget (T)=322026.0458.6
Top1 Prob + BothToken Selection (T.S.)=-, Position Selection (P.S.)=L&E, Randomness Step=all, Compute Budget (T)=322026.0456.8
Top1 Prob + PlannerToken Selection (T.S.)=-, Position Selection (P.S.)=L, Randomness Step=1st, Compute Budget (T)=322026.0455
Init. PositionToken Selection (T.S.)=-, Position Selection (P.S.)=U, Randomness Step=1st, Compute Budget (T)=322026.0452.6
Top1 Prob + EOS Temp.Token Selection (T.S.)=-, Position Selection (P.S.)=E, Randomness Step=all, Compute Budget (T)=322026.0450.9
Prob MarginToken Selection (T.S.)=-, Position Selection (P.S.)=-, Randomness Step=-, Compute Budget (T)=322026.0447.2
Top1 ProbToken Selection (T.S.)=-, Position Selection (P.S.)=-, Randomness Step=-, Compute Budget (T)=322026.0446.6
Temperature SamplingToken Selection (T.S.)=T, Position Selection (P.S.)=-, Randomness Step=all, Compute Budget (T)=322026.0445
Ancestral SamplingToken Selection (T.S.)=-, Position Selection (P.S.)=U, Randomness Step=all, Compute Budget (T)=322026.0442.1