| task,display,n,accuracy,nll,brier,ece,mean_confidence,latency_p50_ms,latency_p95_ms | |
| arc_challenge,ARC-Challenge,1172,0.878839590443686,0.3434354264088279,0.18004018282065612,0.018640702693919233,0.8609673274686053,173.45179200128769,241.31601209974178 | |
| winogrande,WinoGrande,1267,0.664561957379637,0.8732282598352692,0.5079363220206212,0.1986676781891346,0.8493462892926714,168.07529400102794,241.4132092009823 | |
| arc_easy,ARC-Easy,2376,0.9562289562289562,0.15331558248276225,0.07269179989034444,0.029571857402955024,0.9269831239375699,172.40582649901626,231.58336125015921 | |
| hellaswag,HellaSwag,10042,0.8977295359490142,0.2736215284007136,0.14571887516017584,0.012820075397336044,0.8883940220236488,230.12878749796073,276.0439652007335 | |
| mmlu,MMLU,14042,0.6441390115368181,0.8705675106095903,0.45396635565340543,0.03314363695835977,0.6772229938346321,196.04511249963252,303.28189720094076 | |