List your company

Multi-task Language Understanding on MMLU (ACC, F1)

92MMLU AccuracyDIRECT QUERY
34.849.6564.579.35Dec 30, 2023

Evaluation results

MethodLinks
DIRECT QUERYPRIVATE=NO, Backbone=GPT-4O2023.129292
DIRECT QUERYPRIVATE=NO, Backbone=GPT-4-TURBO2023.128971
CONFUSIONPROMPTPRIVATE=YES, Backbone=GPT-4O2023.128990
CONFUSIONPROMPTPRIVATE=YES, Backbone=GPT-4-TURBO2023.128382
DIRECT QUERYPRIVATE=NO, Backbone=GPT-3.5-TURBO2023.127474
CONFUSIONPROMPTPRIVATE=YES, Backbone=GPT-3.5-TURBO2023.127171
VICUNA-13BPRIVATE=YES2023.126060
PARAPHRASERPRIVATE=YES, Backbone=GPT-4O2023.125958
PARAPHRASERPRIVATE=YES, Backbone=GPT-4-TURBO2023.125857
LLAMA2-7BPRIVATE=YES2023.125654
TEXT2TEXTPRIVATE=YES, Backbone=GPT-4O2023.124847
PARAPHRASERPRIVATE=YES, Backbone=GPT-3.5-TURBO2023.124746
TEXT2TEXTPRIVATE=YES, Backbone=GPT-4-TURBO2023.124545
TEXT2TEXTPRIVATE=YES, Backbone=GPT-3.5-TURBO2023.123736