List your company

Multiple Choice Question Answering on MMLU (ACC, ECE, MRR, K-Tau, DRegret)

87.68AccuracyWALLA I
65.184871.024976.86582.7051Jul 5, 2026

Evaluation results

MethodLinks
WALLA Icalibration=calibrated2026.0787.688.2170.7141.029.99
WALLA Ipooling=log-pool2026.0787.362.8872.3225.5510.48
Gemma22026.0787.188.7282.832.6112.94
StackedGen2026.0787.091.9982.2442.1710.6
WALLA II2026.0786.983.0182.5240.4211.7
NIRTRouter2026.0786.912.1582.7243.7211.51
RouteLLM2026.0786.851.9682.7243.7211.03
WALLA I2026.0786.783.3482.645.1111.89
SelfCertainty2026.0786.581.3688.7563.2111.86
RouterDC2026.0785.284.7561.7130.1613.61
UniformAvg2026.0785.155.1—013.87
PackLLM2026.0784.945.1337.79-27.8114.28
Llama3.12026.0781.992.5240.88-8.0117.61
Aloe2026.0780.238.7753.423.6821.34
BioMistral2026.0766.0510.9232.59-28.2739.95