List your company

Logic Reasoning on ARC-Challenge & LogiQA OpenCompass (test)

38.31ARC-C AccuracyCRITIQ
35.481236.215636.9537.6844Feb 26, 2025

Evaluation results

MethodLinks
CRITIQBackbone=Llama-3.2-3B, Continual Pretraining=true, Data Selection Strategy=CRITIQ Scorer2025.0238.3130.4134.36
RawBackbone=Llama-3.2-3B, Continual Pretraining=false2025.0237.9727.3432.66
Zyda-2Backbone=Llama-3.2-3B, Continual Pretraining=true, Data Selection Strategy=Zyda-2 subset2025.0236.6123.530.06
QR-EduBackbone=Llama-3.2-3B, Continual Pretraining=true, Data Selection Strategy=QuRators (Educational Value)2025.0235.5926.8831.24