List your company

Multiple Choice Question Answering on Average (OBQA, ARC, Riddle, PQA)

68.31Average AccuracyLlama-3.1-8B-Instruct
17.3530.5843.8157.04Feb 1, 2026

Evaluation results

MethodLinks
Llama-3.1-8B-InstructSetting=Teacher2026.0268.31
Teacher SelectionSetting=Student, Backbone=FLAN-T5 large (783M)2026.0267.55
Similarity-based RouterSetting=Student, Backbone=FLAN-T5 large (783M)2026.0267.2
PLM ClassifierSetting=Student, Backbone=FLAN-T5 large (783M)2026.0266.4
FLAN-T5 xlargeSetting=Teacher2026.0265.67
Plackett-Luce RankingSetting=Student, Backbone=FLAN-T5 large (783M)2026.0264.5
Knowledge AggregationSetting=Student, Backbone=FLAN-T5 large (783M)2026.0263.32
Fine-tuningSetting=Student, Backbone=FLAN-T5 large (783M)2026.0263.18
Distilling-Step-by-StepSetting=Student, Backbone=FLAN-T5 large (783M)2026.0262.76
TinyLLMSetting=Student, Backbone=FLAN-T5 large (783M)2026.0262.53
Teacher SelectionSetting=Student, Backbone=FLAN-T5 base (248M)2026.0256.68
Similarity-based RouterSetting=Student, Backbone=FLAN-T5 base (248M)2026.0256.56
PLM ClassifierSetting=Student, Backbone=FLAN-T5 base (248M)2026.0256.04
Plackett-Luce RankingSetting=Student, Backbone=FLAN-T5 base (248M)2026.0255.51
Distilling-Step-by-StepSetting=Student, Backbone=FLAN-T5 base (248M)2026.0254.23
Knowledge AggregationSetting=Student, Backbone=FLAN-T5 base (248M)2026.0253.42
Fine-tuningSetting=Student, Backbone=FLAN-T5 base (248M)2026.0253.12
TinyLLMSetting=Student, Backbone=FLAN-T5 base (248M)2026.0252.76
BioMistral-7BSetting=Teacher2026.0249.95
Llama 2-chatSetting=Teacher2026.0249.05
InferenceSetting=Student, Backbone=FLAN-T5 large (783M)2026.0246.69
Similarity-based RouterSetting=Student, Backbone=FLAN-T5 small (77M)2026.0245.66
Teacher SelectionSetting=Student, Backbone=FLAN-T5 small (77M)2026.0244.63
PLM ClassifierSetting=Student, Backbone=FLAN-T5 small (77M)2026.0244.45
Fine-tuningSetting=Student, Backbone=FLAN-T5 small (77M)2026.0243.52
Plackett-Luce RankingSetting=Student, Backbone=FLAN-T5 small (77M)2026.0242.49
TinyLLMSetting=Student, Backbone=FLAN-T5 small (77M)2026.0242.38
Knowledge AggregationSetting=Student, Backbone=FLAN-T5 small (77M)2026.0242.01
Distilling-Step-by-StepSetting=Student, Backbone=FLAN-T5 small (77M)2026.0241.47
InferenceSetting=Student, Backbone=FLAN-T5 base (248M)2026.0232.7
InferenceSetting=Student, Backbone=FLAN-T5 small (77M)2026.0219.31