List your company

Multitask Language Understanding on MMLU-pro (RA)

59.33RACortexDebate
45.466849.065952.66556.2641Jul 5, 2025

Evaluation results

MethodLinks
CortexDebateType=Ours2025.0759.33
MDMType=Part Debate2025.0758.9
PRDType=Full Debate2025.0754.2
PRDType=Full Debate2025.0754
RECONCILEType=Full Debate2025.0753.67
RECONCILEType=Full Debate2025.0753.1
GDType=Part Debate2025.0751.67
GDType=Part Debate2025.0751.3
ChatEvalType=Full Debate2025.0749.33
ChatEvalType=Full Debate2025.0749.3
NDType=Part Debate2025.0749.1
NDType=Part Debate2025.0748.67
MLDType=Full Debate2025.0748.4
MLDType=Full Debate2025.0747.33
MaVType=No Debate2025.0746.3
MaVType=No Debate2025.0746