ResearchBenchmarksRanking Prediction on MATH-plus R1Follow0.73Kendall's TauPARS0.5220.5760.630.684Sep 25, 2025Evaluation ResultsMethodMethodLinksKendall's TauPARSRanking Approach=PairwiseRanking Approach=Pairwise2025.090.73Listwise2025.090.63Pointwise2025.090.55PARSRanking Approach=Cross...Ranking Approach=Cross-Model2025.090.53