SOTA Paraphrase Identification benchmarks and papers with code

Benchmarks

Dataset Name	SOTA Method	Metric
QQP	SMP-S	Accuracy91.7	78	3d ago
Quora Question Pairs (test)	DRCN	Accuracy91.3	72	3d ago
PAWS-X	ByT5	Accuracy91.7	57	3d ago
MRPC	Qwen2.5-14B	Delta 1-4.73	24	3d ago
TwitterPara (test)	SBERT-supervised	TURL81.6	22	3d ago
PAWS -> PAWS (test)		Accuracy94.1	22	3d ago
QQP Out-of-distribution from PAWS	GAPX	Macro F170.8	20	3d ago
PAWS -> QQP (test)	GAPX	AUROC77.7	20	3d ago
PIT -> PAWS (test)	OODP	AUROC77.5	20	3d ago
PAWS	In-Squeeze	Accuracy97.6	17	3d ago
QQP few-shot zero-shot	RETROPROMPT	Accuracy74	16	3d ago
MCEval PAWS 8K (test)	Act	Accuracy88.9	14	3d ago
Quora Question Pairs	SA-DiffuSeq	Accuracy95.3	14	3d ago
Quora Question Pairs (dev)	DIIN	Accuracy90.48	14	3d ago
PAWS-X (test)	mBERT (Reference [1])	Accuracy (en)94	13	2d ago
PAWS-X	TokAlign + LAT	Accuracy (de)54.6	12	3d ago
WMT Out-of-distribution from PAWS	GAPX	Macro F176.4	10	3d ago
PIT Out-of-distribution from PAWS	OODP	Macro F169.8	10	3d ago
PAWS Out-of-distribution from PIT	GAPX	Macro F155.1	10	3d ago
QQP Out-of-distribution from PIT	OODP	Macro F10.757	10	3d ago
WMT Out-of-distribution from QQP	GAPX	Macro F175.5	10	3d ago
QQP, PAWS, and PIT In-distribution (test)		AUROC (QQP->QQP)92	10	3d ago
PAWS -> WMT (test)	OODP	AUROC0.849	10	3d ago
PIT -> WMT (test)	OODP	AUROC0.85	10	3d ago
QQP -> WMT (test)	GAP	AUROC85.1	10	3d ago

Showing 25 of 39 rows