List your company

Multi-task Language Understanding on MMLU-pro

14,946.31Average Context Length (tokens)PRD
1,632.31325,088.83168,545.3512,001.8684Jul 5, 2025

Evaluation results

MethodLinks
PRDType=Full Debate2025.0714,946.31
PRDType=Full Debate2025.0714,829.46
MLDType=Full Debate2025.0711,412.75
RECONCILEType=Full Debate2025.0711,334.12
RECONCILEType=Full Debate2025.0711,260.15
MLDType=Full Debate2025.0711,213.07
ChatEvalType=Full Debate2025.079,219.88
ChatEvalType=Full Debate2025.079,160.49
GDType=Part Debate2025.077,265.23
GDType=Part Debate2025.077,159.45
NDType=Part Debate2025.076,673.75
NDType=Part Debate2025.076,647.27
OursType=Part Debate2025.076,001.33
OursType=Part Debate2025.075,897.94
MaVType=No Debate2025.072,268.1
MaVType=No Debate2025.072,144.39