task,display,n,accuracy,nll,brier,ece,mean_confidence,latency_p50_ms,latency_p95_ms arc_challenge,ARC-Challenge,1172,0.8737201365187713,0.6831067400476731,0.21717192716282274,0.0939787680494793,0.9676989045682511,158.1707515015296,239.32236594882852 winogrande,WinoGrande,1267,0.601420678768745,1.2788768116978686,0.6614413444986983,0.3052572014015491,0.9024290672675535,154.72152499933145,223.75241669906248 arc_easy,ARC-Easy,2376,0.9558080808080808,0.22179265867232187,0.07866352502747752,0.03341212654329345,0.9868527784304538,153.7982515001204,216.1515892476018 hellaswag,HellaSwag,10042,0.7650866361282613,1.1006902005839516,0.3895498661609883,0.16545367857507678,0.9305298846809178,259.9183570000605,484.0487622521322 mmlu,MMLU,14042,0.6618715282723259,1.6791403682676391,0.5577819683925032,0.24181974065906128,0.9036912689313833,176.33997150187497,324.31165310117643