Text Classification on TweetEVAL (test)
84.17Accuracy (A)ProtoSiTex
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ProtoSiTexCategory=Prototypical Models2025.10 | 84.17 | 84.12 | |
| TweetNLPCategory=SOTA for TweetEVAL and IMDB2025.10 | 84.09 | 83.9 | |
| BERTweetCategory=SOTA for TweetEVAL and IMDB2025.10 | 83.95 | 83.8 | |
| RoBERTa-LargeCategory=Masked-based Models2025.10 | 83.18 | 82.83 | |
| Llama3.2-3BCategory=Autoregressive Models2025.10 | 82.69 | 82.38 | |
| Llama3.3-70B-instructCategory=Open-source LLMs2025.10 | 81.98 | 82.16 | |
| Nomic Embed Text V2Category=Masked-based Models2025.10 | 81.91 | 81.49 | |
| GAProtoNetCategory=Prototypical Models2025.10 | 81.84 | 81.85 | |
| DeBERTaV3Category=Masked-based Models2025.10 | 81.63 | 81.38 | |
| ELECTRACategory=Masked-based Models2025.10 | 81.14 | 80.92 | |
| GPT-5-nanoCategory=Closed-source LLMs2025.10 | 80.92 | 81.44 | |
| NeoBERTCategory=Masked-based Models2025.10 | 80.86 | 80.59 | |
| RoBERTaCategory=Masked-based Models2025.10 | 80.78 | 80.66 | |
| Mistral-small-3.2-24BCategory=Open-source LLMs2025.10 | 80.64 | 79.76 | |
| BertGCNCategory=Graph-based Text Classification2025.10 | 80.43 | 80.8 | |
| Qwen2.5-72B-instructCategory=Open-source LLMs2025.10 | 80.15 | 80.55 | |
| Gemini-2.5-flashCategory=Closed-source LLMs2025.10 | 80.08 | 80.26 | |
| Deepseek-chat-v3.2Category=Closed-source LLMs2025.10 | 79.94 | 80.3 | |
| BERTCategory=Masked-based Models2025.10 | 79.73 | 79.39 | |
| DistilBERTCategory=Masked-based Models2025.10 | 79.59 | 79.16 | |
| Phi-4-mini-instructCategory=Autoregressive Models2025.10 | 79.24 | 79.05 | |
| Qwen3-4BCategory=Autoregressive Models2025.10 | 78.68 | 78.48 | |
| ModernBERT-LargeCategory=Masked-based Models2025.10 | 77.76 | 77.33 | |
| XLNetCategory=Autoregressive Models2025.10 | 77.2 | 77.11 | |
| UCLAFCategory=Multi-label Text Classification2025.10 | 76.28 | 76.04 | |
| SentiCSECategory=SOTA for TweetEVAL and IMDB2025.10 | 76.07 | 75.68 | |
| ALBERTCategory=Masked-based Models2025.10 | 75.58 | 74.98 | |
| ProtoTEXCategory=Prototypical Models2025.10 | 75.28 | 75.2 | |
| ProSeNetCategory=Prototypical Models2025.10 | 73.24 | 73.54 | |
| ModernBERTCategory=Masked-based Models2025.10 | 73.18 | 73.16 | |
| ProtoryNetCategory=Prototypical Models2025.10 | 72.9 | 72.28 | |
| MAGNETCategory=Multi-label Text Classification2025.10 | 72.27 | 70.39 | |
| SETFITCategory=SOTA for TweetEVAL and IMDB2025.10 | 70.09 | 71.07 | |
| Glove + BiLSTMCategory=Traditional Text Classification2025.10 | 63.35 | 59.75 | |
| TextGCNCategory=Graph-based Text Classification2025.10 | 62.14 | 61.36 | |
| Label power setCategory=Multi-label Text Classification2025.10 | 60.89 | 60.02 | |
| Word2Vec + BiLSTMCategory=Traditional Text Classification2025.10 | 60.87 | 55.79 | |
| Binary RelevanceCategory=Multi-label Text Classification2025.10 | 59.95 | 59.11 | |
| FastText + BiLSTMCategory=Traditional Text Classification2025.10 | 59.81 | 56.8 | |
| Classifier ChainCategory=Multi-label Text Classification2025.10 | 55.59 | 52.86 | |
| ML-KNNCategory=Multi-label Text Classification2025.10 | 55.31 | 54.95 | |
| ProtoLensCategory=Prototypical Models2025.10 | 50.59 | 51.05 | |
| MLTC1Category=Multi-label Text Classification2025.10 | 33.07 | 33.57 | |
| Proto-lmCategory=Prototypical Models2025.10 | 22.15 | 39.26 |