Sentiment Analysis on SST-5 Fine-grained classification

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	Llama-3.3-70B + CAPO	62.27	No	CAPO: Cost-Aware Prompt Optimization	2025-04-22	Code
2	Heinsen Routing + RoBERTa Large	59.8	No	An Algorithm for Routing Vectors in Sequences	2022-11-20	Code
3	RoBERTa-large+Self-Explaining	59.1	No	Self-Explaining Structures Improve NLP Models	2020-12-03	Code
4	Heinsen Routing + GPT-2	58.5	No	An Algorithm for Routing Capsules in All Domains	2019-11-02	Code
5	BCN+Suffix BiLSTM-Tied+CoVe	56.2	No	Improved Sentence Modeling using Suffix Bidirect...	2018-05-18	-
6	BERT Large	55.5	No	Fine-grained Sentiment Classification using BERT	2019-10-04	Code
7	LM-CPPF RoBERTa-base	54.9	No	LM-CPPF: Paraphrasing-Guided Data Augmentation f...	2023-05-29	Code
8	BCN+ELMo	54.7	No	Deep contextualized word representations	2018-02-15	Code
9	byte mLSTM7	54.6	No	A La Carte Embedding: Cheap but Effective Induct...	2018-05-14	Code
10	BCN+Char+CoVe	53.7	No	Learned in Translation: Contextualized Word Vect...	2017-08-01	Code
11	Bi-CAS-LSTM	53.6	No	Cell-aware Stacked LSTMs for Modeling Sentences	2018-09-07	-
12	CNN-RNF-LSTM	53.4	No	Convolutional Neural Networks with Recurrent Neu...	2018-08-28	Code
13	BERT Base	53.2	No	Fine-grained Sentiment Classification using BERT	2019-10-04	Code
14	Star-Transformer	53	No	Star-Transformer	2019-02-25	Code
15	BP-Transformer + GloVe	52.71	No	BP-Transformer: Modelling Long-Range Context via...	2019-11-11	Code
16	MEAN	51.4	No	A Multi-sentiment-resource Enhanced Attention Ne...	2018-07-13	-
17	Constituency Tree-LSTM	51	No	Improved Semantic Representations From Tree-Stru...	2015-02-28	Code
18	Bi-LSTM+2+5	50.4	No	Leveraging Multi-grained Sentiment Lexicon Infor...	2018-12-04	-
19	MPAD-path	49.68	No	Message Passing Attention Networks for Document ...	2019-08-17	Code
20	Epic	49.6	No	-	-	Code
21	RNN-Capsule	49.3	No	-	-	Code
22	C-LSTM	49.2	No	A C-LSTM Neural Network for Text Classification	2015-11-27	Code
23	STM+TSED+PT+2L	49.14	No	The Pupil Has Become the Master: Teacher-Student...	2019-05-31	Code
24	SWEM-concat	46.1	No	Baseline Needs More Love: On Simple Word-Embeddi...	2018-05-24	Code
25	GRU-RNN-WORD2VEC	45.02	No	All-but-the-Top: Simple and Effective Postproces...	2017-02-05	Code
26	Joined Model Multi-tasking	44.82	No	-	-	-
27	MV-RNN	44.4	No	-	-	Code
28	GloVe+Emo2Vec	43.6	No	Emo2Vec: Learning Generalized Emotion Representa...	2018-09-12	Code
29	Emo2Vec	41.6	No	Emo2Vec: Learning Generalized Emotion Representa...	2018-09-12	Code

#1Llama-3.3-70B + CAPOSOTA
62.27
Accuracy· 2025-04-22
CAPO: Cost-Aware Prompt Optimization Code
#2Heinsen Routing + RoBERTa LargeSOTA
59.8
Accuracy· 2022-11-20
An Algorithm for Routing Vectors in Sequences Code
#3RoBERTa-large+Self-ExplainingSOTA
59.1
Accuracy· 2020-12-03
Self-Explaining Structures Improve NLP Models Code
#4Heinsen Routing + GPT-2SOTA
58.5
Accuracy· 2019-11-02
An Algorithm for Routing Capsules in All Domains Code
#5BCN+Suffix BiLSTM-Tied+CoVeSOTA
56.2
Accuracy· 2018-05-18
Improved Sentence Modeling using Suffix Bidirectional LSTM
#6BERT Large
55.5
Accuracy· 2019-10-04
Fine-grained Sentiment Classification using BERT Code
#7LM-CPPF RoBERTa-base
54.9
Accuracy· 2023-05-29
LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning Code
#8BCN+ELMoSOTA
54.7
Accuracy· 2018-02-15
Deep contextualized word representations Code
#9byte mLSTM7
54.6
Accuracy· 2018-05-14
A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors Code
#10BCN+Char+CoVeSOTA
53.7
Accuracy· 2017-08-01
Learned in Translation: Contextualized Word Vectors Code
#11Bi-CAS-LSTM
53.6
Accuracy· 2018-09-07
Cell-aware Stacked LSTMs for Modeling Sentences
#12CNN-RNF-LSTM
53.4
Accuracy· 2018-08-28
Convolutional Neural Networks with Recurrent Neural Filters Code
#13BERT Base
53.2
Accuracy· 2019-10-04
Fine-grained Sentiment Classification using BERT Code
#14Star-Transformer
53
Accuracy· 2019-02-25
Star-Transformer Code
#15BP-Transformer + GloVe
52.71
Accuracy· 2019-11-11
BP-Transformer: Modelling Long-Range Context via Binary Partitioning Code
#16MEAN
51.4
Accuracy· 2018-07-13
A Multi-sentiment-resource Enhanced Attention Network for Sentiment Classification
#17Constituency Tree-LSTMSOTA
51
Accuracy· 2015-02-28
Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks Code
#18Bi-LSTM+2+5
50.4
Accuracy· 2018-12-04
Leveraging Multi-grained Sentiment Lexicon Information for Neural Sequence Models
#19MPAD-path
49.68
Accuracy· 2019-08-17
Message Passing Attention Networks for Document Understanding Code
#20Epic
49.6
Accuracy
No paperCode
#21RNN-Capsule
49.3
Accuracy
No paperCode
#22C-LSTM
49.2
Accuracy· 2015-11-27
A C-LSTM Neural Network for Text Classification Code
#23STM+TSED+PT+2L
49.14
Accuracy· 2019-05-31
The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learning Code
#24SWEM-concat
46.1
Accuracy· 2018-05-24
Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms Code
#25GRU-RNN-WORD2VEC
45.02
Accuracy· 2017-02-05
All-but-the-Top: Simple and Effective Postprocessing for Word Representations Code
#26Joined Model Multi-tasking
44.82
Accuracy
No paper
#27MV-RNN
44.4
Accuracy
No paperCode
#28GloVe+Emo2Vec
43.6
Accuracy· 2018-09-12
Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training Code
#29Emo2Vec
41.6
Accuracy· 2018-09-12
Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training Code