List your company

Multiple Choice Question Answering on MedMCQA i.d.

82.66AccuracyStackedGen
46.062455.563765.06574.5663Jul 5, 2026

Evaluation results

MethodLinks
StackedGen2026.0782.662.2159.0630.9111.56
WALLA Icalibration=calibrated2026.0782.5310.5665.9838.9211.69
RouteLLM2026.0781.73.6255.6427.6712.82
WALLA I2026.0781.177.5955.2624.1714.86
NIRTRouter2026.0781.156.9955.6427.6714.56
WALLA II2026.07817.8555.321.9515.36
WALLA Ipooling=log-pool2026.0780.322.0755.0123.1514.58
Aloe2026.0779.773.1859.4914.4215.77
PackLLM2026.07799.9350.778.8518.93
Llama3.12026.0778.972.6451.564.4715.97
RouterDC2026.0778.958.7755.6527.6518.35
UniformAvg2026.0776.458.1—021.05
SelfCertainty2026.0774.424.5879.7843.6122.08
Gemma22026.0762.925.2864.995.9347.28
BioMistral2026.0747.4717.137.71-24.8256.24