List your company

Code-writing on HumanEval & MBPP EvalPlus (test)

39.02HumanEval Pass RateCRITIQ
28.245631.042833.8436.6372Feb 26, 2025

Evaluation results

MethodLinks
CRITIQBackbone=Llama-3.2-3B, Continual Pretraining=true, Data Selection Strategy=CRITIQ Scorer2025.0239.0233.5468.7348.4153.8840.98
QR-EduBackbone=Llama-3.2-3B, Continual Pretraining=true, Data Selection Strategy=QuRators (Educational Value)2025.0236.5932.3259.2647.3547.9339.84
StackBackbone=Llama-3.2-3B, Continual Pretraining=true, Data Selection Strategy=Stack v2 subset2025.0231.7127.4456.6146.344.1636.87
RawBackbone=Llama-3.2-3B, Continual Pretraining=false2025.0228.6625.6148.9439.1538.832.38