List your company

Complexity Prediction on MMLU+MMLU-PRO+GSM8K

89.1ROC-AUCIntroLM
73.70877.70481.785.696Jan 7, 2026

Evaluation results

MethodLinks
IntroLMBackbone Model=Qwen3-8B2026.0189.163.4
DeBERTa-v3-LargeNumber of Parameters=435M, Backbone Model=DeBERTa-v3-Large2026.0175.845.5
DeBERTa-v3-BaseNumber of Parameters=184M, Backbone Model=DeBERTa-v3-Base2026.0174.344.3