List your company

Question Answering on ARC Challenging

15.65LLMcritic CallsVecCISC + KMeans
10.751612.023313.29514.5667May 8, 2026

Evaluation results

MethodLinks
VecCISC + KMeansBudget=20, Backbone=Mistral 7B, Cluster candidate selection=min-centroid2026.0515.65-21.73
VecCISC + KMeansBudget=20, Backbone=Llama 3.1 8B, Cluster candidate selection=min-centroid2026.0514.8-26
VecCISC + KMeansBudget=20, Backbone=GPT-4o mini, Cluster candidate selection=min-centroid2026.0513.34-33.29
VecCISC + KMeansBudget=20, Backbone=Llama3.3 70B, Cluster candidate selection=min-centroid2026.0513.31-33.43
VecCISC + KMeansBudget=20, Backbone=Qwen2.5 7B, Cluster candidate selection=min-centroid2026.0510.94-45.3