Share your thoughts, 1 month free Claude Pro on usSee more

Factual Consistency Evaluation on 2,055 code summary evaluations

0Time (s)

ROUGE-1

Updated 4d ago

Evaluation Results

Method	Links
ROUGE-1 2026.04		0	0
ROUGE-2 2026.04		0	0
ROUGE-L 2026.04		0	0
METEOR 2026.04		0.02	0
SBCS 2026.04		0.02	0
BERTScore 2026.04		0.03	0
SBED 2026.04		0.03	0
SIDE 2026.04		0.08	0
LLM-judge 2026.04		0.34	0.0002
CODERPE 2026.04		0.53	0.0002
G-Eval 2026.04		1.11	0.0002
BLEU 2026.04		1.12	0
Factscore 2026.04		9.18	0.0058
ReFEree 2026.04		10.24	0.0042