Multi-label Text Classification on Hotel Reviews (HR) (test) benchmark leaderboard · SOTA2 Research

Multi-label Text Classification on Hotel Reviews (HR) (test)

87.23F-MeasureRoBERTa-Large

Evaluation Results

Method	Links
RoBERTa-Large2025.10		87.23	84.59	12.04
ProtoSiTex2025.10		87.22	83.68	12.35
XLNet2025.10		86.95	83.51	13.25
ELECTRA2025.10		86.78	81.16	13.56
ModernBERT-Large2025.10		86.76	82.36	13.37
BertGCN2025.10		86.55	74.56	16.12
RoBERTa2025.10		86.47	83.41	12.77
NeoBERT2025.10		86.26	82.79	12.92
DeBERTaV32025.10		86.24	80.09	13.85
BERT2025.10		86.16	82.01	12.53
ModernBERT2025.10		85.6	83.21	14.11
DistilBERT2025.10		84.96	81.14	14.11
Llama3.2-3B2025.10		84.14	80.37	15.02
ALBERT2025.10		83.73	77.54	14.77
Nomic Embed Text V22025.10		83.06	77.41	15.06
Qwen3-4B2025.10		81.34	76.54	18.07
TweetNLP2025.10		80.44	76.28	17.89
Phi-4-mini-instruct2025.10		80.31	75.2	18.7
BERTweet2025.10		80.1	76.94	18.01
TextGCN2025.10		78.37	64.07	22.88
Gemini-2.5-flash2025.10		78.35	74.95	20.56
ProtoTEX2025.10		77.24	38.1	24.6
MAGNET2025.10		76.42	56.01	27.47
GPT-5-nano2025.10		76.33	73.49	21.5
MLTC12025.10		74.43	51.15	36.62
ProSeNet2025.10		74.31	50	38.42
ProtoLens2025.10		74.31	50	38.42
UCLAF2025.10		73.3	61.99	23.41
Label power set2025.10		72.79	62.9	28.05
GAProtoNet2025.10		72.31	48.13	23.6
SETFIT2025.10		72.23	70.55	18.01
Deepseek-chat-v3.22025.10		72.11	73.37	23.96
ML-KNN2025.10		72.09	60.65	28.14
Binary Relevance2025.10		70.81	66.94	31.59
Classifier Chain2025.10		70.66	66.83	31.78
SentiCSE2025.10		69.22	66.92	22.46
Llama3.3-70B-instruct2025.10		65.16	63.38	33.19
Glove + BiLSTM2025.10		64.74	62.36	23.04
ProtoryNet2025.10		62.57	50	28.77
Proto-lm2025.10		62.44	49.88	28.94
Word2Vec + BiLSTM2025.10		61.72	58.15	26.47
Qwen2.5-72B-instruct2025.10		61.44	66.76	31.78
FastText + BiLSTM2025.10		61.32	58.9	27.2
Mistral-small-3.2-24B2025.10		61.03	65.77	32.48