Our new X account is live! Follow @wizwand_team for updates

Meta-evaluation on SummEval

0.448Spearman Correlation (COH)

BARTSCORE-CNN

Updated 4d ago

Evaluation Results

Method	Links
BARTSCORE-CNN 2021.06		0.448	-	-	-	-	0.382	0.356	0.356	0.499	-
BARTSCORE-CNN-PARA 2021.06		0.424	-	-	-	-	0.401	0.378	0.313	0.497	-
BARTSCORE-PROMPT 2021.06		0.407	-	-	-	-	0.378	0.338	0.368	0.518	-
BARTSCORE 2021.06		0.322	-	-	-	-	0.311	0.248	0.264	0.465	-
BERTScore 2021.06		0.284	-	-	-	-	0.11	0.193	0.312	0.217	-
PRISM 2021.06		0.249	-	-	-	-	0.345	0.254	0.212	0.41	-
ROUGE-2 2021.06		0.184	-	-	-	-	0.187	0.159	0.29	0.165	-
ROUGE-1 2021.06		0.167	-	-	-	-	0.16	0.115	0.326	0.194	-
MoverScore 2021.06		0.159	-	-	-	-	0.157	0.129	0.318	0.2	-
ROUGE-L 2021.06		0.128	-	-	-	-	0.115	0.105	0.311	0.164	-
GPT-4o 2025.02		-	0.58	83.5	0.562	0.522	-	-	-	-	-
GPT-4o mini 2025.02		-	0.393	81.5	0.521	0.507	-	-	-	-	-
GPT-4 Turbo 2025.02		-	0.741	83.9	0.625	0.513	-	-	-	-	-
Llama-3.1-70B 2025.02		-	0.402	80.7	0.523	0.491	-	-	-	-	-
Qwen-2.5-72B 2025.02		-	0.518	84	0.577	0.49	-	-	-	-	-
Gemma-2-27B 2025.02		-	0.527	84.2	0.533	0.49	-	-	-	-	-
Phi-4-14B 2025.02		-	0.68	81.5	0.564	0.532	-	-	-	-	-
G-EVAL-3.5 2023.05		-	-	-	-	-	-	-	-	-	38.6
G-EVAL-4 2023.05		-	-	-	-	-	-	-	-	-	50.7
GPTScore 2023.05		-	-	-	-	-	-	-	-	-	47.5
ChatGPT 2023.05		-	-	-	-	-	-	-	-	-	43.3
ALIGNSCORE-base 2023.05		-	-	-	-	-	-	-	-	-	43.4
ALIGNSCORE-large 2023.05		-	-	-	-	-	-	-	-	-	46.6