Natural Language Inference on WNLI

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	Turing NLR v5 XXL 5.4B (fine-tuned)	95.9	No	Toward Efficient Language Model Pretraining and ...	2022-12-04	-
2	DeBERTa	94.5	No	DeBERTa: Decoding-enhanced BERT with Disentangle...	2020-06-05	Code
3	T5-XXL 11B	93.2	No	Exploring the Limits of Transfer Learning with a...	2019-10-23	Code
4	XLNet	92.5	No	XLNet: Generalized Autoregressive Pretraining fo...	2019-06-19	Code
5	ALBERT	91.8	No	ALBERT: A Lite BERT for Self-supervised Learning...	2019-09-26	Code
6	T5-XL 3B	89.7	No	Exploring the Limits of Transfer Learning with a...	2019-10-23	Code
7	StructBERTRoBERTa ensemble	89.7	No	StructBERT: Incorporating Language Structures in...	2019-08-13	-
8	HNNensemble	89	No	A Hybrid Neural Network Model for Commonsense Re...	2019-07-27	Code
9	RoBERTa (ensemble)	89	No	RoBERTa: A Robustly Optimized BERT Pretraining A...	2019-07-26	Code
10	T5-Large 770M	85.6	No	Exploring the Limits of Transfer Learning with a...	2019-10-23	Code
11	HNN	83.6	No	A Hybrid Neural Network Model for Commonsense Re...	2019-07-27	Code
12	T5-Base 220M	78.8	No	Exploring the Limits of Transfer Learning with a...	2019-10-23	Code
13	BERTwiki 340M (fine-tuned on WSCR)	74.7	No	A Surprisingly Robust Trick for Winograd Schema ...	2019-05-15	Code
14	FLAN 137B (zero-shot)	74.6	No	Finetuned Language Models Are Zero-Shot Learners	2021-09-03	Code
15	BERT-large 340M (fine-tuned on WSCR)	71.9	No	A Surprisingly Robust Trick for Winograd Schema ...	2019-05-15	Code
16	BERT-base 110M (fine-tuned on WSCR)	70.5	No	A Surprisingly Robust Trick for Winograd Schema ...	2019-05-15	Code
17	FLAN 137B (few-shot, k=4)	70.4	No	Finetuned Language Models Are Zero-Shot Learners	2021-09-03	Code
18	T5-Small 60M	69.2	No	Exploring the Limits of Transfer Learning with a...	2019-10-23	Code
19	ERNIE 2.0 Large	67.8	No	ERNIE 2.0: A Continual Pre-training Framework fo...	2019-07-29	Code
20	SqueezeBERT	65.1	No	SqueezeBERT: What can computer vision teach NLP ...	2020-06-19	Code
21	BERT-large 340M	65.1	No	BERT: Pre-training of Deep Bidirectional Transfo...	2018-10-11	Code
22	RWKV-4-Raven-14B	49.3	No	RWKV: Reinventing RNNs for the Transformer Era	2023-05-22	Code
23	DistilBERT 66M	44.4	No	DistilBERT, a distilled version of BERT: smaller...	2019-10-02	Code

#1Turing NLR v5 XXL 5.4B (fine-tuned)SOTA
95.9
Accuracy· 2022-12-04
Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
#2DeBERTaSOTA
94.5
Accuracy· 2020-06-05
DeBERTa: Decoding-enhanced BERT with Disentangled Attention Code
#3T5-XXL 11BSOTA
93.2
Accuracy· 2019-10-23
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer Code
#4XLNetSOTA
92.5
Accuracy· 2019-06-19
XLNet: Generalized Autoregressive Pretraining for Language Understanding Code
#5ALBERT
91.8
Accuracy· 2019-09-26
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations Code
#6T5-XL 3B
89.7
Accuracy· 2019-10-23
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer Code
#7StructBERTRoBERTa ensemble
89.7
Accuracy· 2019-08-13
StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding
#8HNNensemble
89
Accuracy· 2019-07-27
A Hybrid Neural Network Model for Commonsense Reasoning Code
#9RoBERTa (ensemble)
89
Accuracy· 2019-07-26
RoBERTa: A Robustly Optimized BERT Pretraining Approach Code
#10T5-Large 770M
85.6
Accuracy· 2019-10-23
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer Code
#11HNN
83.6
Accuracy· 2019-07-27
A Hybrid Neural Network Model for Commonsense Reasoning Code
#12T5-Base 220M
78.8
Accuracy· 2019-10-23
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer Code
#13BERTwiki 340M (fine-tuned on WSCR)SOTA
74.7
Accuracy· 2019-05-15
A Surprisingly Robust Trick for Winograd Schema Challenge Code
#14FLAN 137B (zero-shot)
74.6
Accuracy· 2021-09-03
Finetuned Language Models Are Zero-Shot Learners Code
#15BERT-large 340M (fine-tuned on WSCR)
71.9
Accuracy· 2019-05-15
A Surprisingly Robust Trick for Winograd Schema Challenge Code
#16BERT-base 110M (fine-tuned on WSCR)
70.5
Accuracy· 2019-05-15
A Surprisingly Robust Trick for Winograd Schema Challenge Code
#17FLAN 137B (few-shot, k=4)
70.4
Accuracy· 2021-09-03
Finetuned Language Models Are Zero-Shot Learners Code
#18T5-Small 60M
69.2
Accuracy· 2019-10-23
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer Code
#19ERNIE 2.0 Large
67.8
Accuracy· 2019-07-29
ERNIE 2.0: A Continual Pre-training Framework for Language Understanding Code
#20SqueezeBERT
65.1
Accuracy· 2020-06-19
SqueezeBERT: What can computer vision teach NLP about efficient neural networks?Code
#21BERT-large 340MSOTA
65.1
Accuracy· 2018-10-11
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding Code
#22RWKV-4-Raven-14B
49.3
Accuracy· 2023-05-22
RWKV: Reinventing RNNs for the Transformer Era Code
#23DistilBERT 66M
44.4
Accuracy· 2019-10-02
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter Code