Text Classification on English Dataset benchmark leaderboard · SOTA2 Research

Text Classification on English Dataset

0.9148AccuracyMulti-lingual BERT

Evaluation Results

Method	Links
Multi-lingual BERT2025.12		0.9148	0.945	0.81	0.8733
XLM-Roberta2025.12		0.9072	0.8504	0.8415	0.8459
Semi-SMDNet2025.12		0.885	0.885	0.885	0.885
LLM Semi-supervised (LLM-SS)2025.12		0.8631	0.8483	0.7365	0.7885
Hybrid Explainability (IIE)2025.12		0.8572	0.86	0.86	0.86
Semi-SMDNet2025.12		0.8426	0.8415	0.8645	0.8528
Multi-lingual BERT2025.12		0.8324	0.8479	0.8465	0.8472
XLM-Roberta2025.12		0.8211	0.8275	0.8355	0.8315
GPT-42025.12		0.8171	0.7805	0.878	0.8265
LLM Semi-supervised (LLM-SS)2025.12		0.6916	0.6653	0.643	0.654
Hybrid Explainability (IIE)2025.12		0.6858	0.688	0.688	0.688