Subjectivity Analysis on SUBJ

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	RoBERTa+DualCL	97.34	No	Dual Contrastive Learning: Text Classification v...	2022-01-21	Code
2	BERT-Base + CLR + LSTM	97.3	No	-	-	Code
3	RoBERTa-large 355M + Entailment as Few-shot Learner	97.1	No	Entailment as Few-Shot Learner	2021-04-29	Code
4	BERT-Base + LSTM	96.6	No	-	-	Code
5	AdaSent	95.5	No	Self-Adaptive Hierarchical Sentence Model	2015-04-20	Code
6	VLAWE	95	No	Vector of Locally-Aggregated Word Embeddings (VL...	2019-02-23	Code
7	CNN+MCFA	94.8	No	Translations as Additional Contexts for Sentence...	2018-06-14	Code
8	byte mLSTM7	94.7	No	A La Carte Embedding: Cheap but Effective Induct...	2018-05-14	Code
9	Byte mLSTM	94.6	No	Learning to Generate Reviews and Discovering Sen...	2017-04-05	Code
10	USE	93.9	No	Universal Sentence Encoder	2018-03-29	Code
11	Capsule-B	93.8	No	Investigating Capsule Networks with Dynamic Rout...	2018-03-29	Code
12	Fast Dropout	93.6	No	-	-	-
13	SWEM-concat	93	No	Baseline Needs More Love: On Simple Word-Embeddi...	2018-05-24	Code
14	STM+TSED+PT+2L	92.34	No	The Pupil Has Become the Master: Teacher-Student...	2019-05-31	Code
15	GRU-RNN-GLOVE	91.85	No	All-but-the-Top: Simple and Effective Postproces...	2017-02-05	Code
16	Llama-3.3-70B + CAPO	91.6	No	CAPO: Cost-Aware Prompt Optimization	2025-04-22	Code
17	Qwen2.5-32B + CAPO	91	No	CAPO: Cost-Aware Prompt Optimization	2025-04-22	Code
18	SDAE	90.8	No	Learning Distributed Representations of Sentence...	2016-02-10	Code
19	Mistral-Small-24B + CAPO	81.67	No	CAPO: Cost-Aware Prompt Optimization	2025-04-22	Code

#1RoBERTa+DualCLSOTA
97.34
Accuracy· 2022-01-21
Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation Code
#2BERT-Base + CLR + LSTM
97.3
Accuracy
No paperCode
#3RoBERTa-large 355M + Entailment as Few-shot LearnerSOTA
97.1
Accuracy· 2021-04-29
Entailment as Few-Shot Learner Code
#4BERT-Base + LSTM
96.6
Accuracy
No paperCode
#5AdaSentSOTA
95.5
Accuracy· 2015-04-20
Self-Adaptive Hierarchical Sentence Model Code
#6VLAWE
95
Accuracy· 2019-02-23
Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation Code
#7CNN+MCFA
94.8
Accuracy· 2018-06-14
Translations as Additional Contexts for Sentence Classification Code
#8byte mLSTM7
94.7
Accuracy· 2018-05-14
A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors Code
#9Byte mLSTM
94.6
Accuracy· 2017-04-05
Learning to Generate Reviews and Discovering Sentiment Code
#10USE
93.9
Accuracy· 2018-03-29
Universal Sentence Encoder Code
#11Capsule-B
93.8
Accuracy· 2018-03-29
Investigating Capsule Networks with Dynamic Routing for Text Classification Code
#12Fast Dropout
93.6
Accuracy
No paper
#13SWEM-concat
93
Accuracy· 2018-05-24
Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms Code
#14STM+TSED+PT+2L
92.34
Accuracy· 2019-05-31
The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learning Code
#15GRU-RNN-GLOVE
91.85
Accuracy· 2017-02-05
All-but-the-Top: Simple and Effective Postprocessing for Word Representations Code
#16Llama-3.3-70B + CAPO
91.6
Accuracy· 2025-04-22
CAPO: Cost-Aware Prompt Optimization Code
#17Qwen2.5-32B + CAPO
91
Accuracy· 2025-04-22
CAPO: Cost-Aware Prompt Optimization Code
#18SDAE
90.8
Accuracy· 2016-02-10
Learning Distributed Representations of Sentences from Unlabelled Data Code
#19Mistral-Small-24B + CAPO
81.67
Accuracy· 2025-04-22
CAPO: Cost-Aware Prompt Optimization Code