List your company
ResearchFormerly WizWand

Named Entity Recognition on GENIA

83.8F1 ScoreBERT-MRC
-3.35219.27441.964.526Oct 3, 2018Jan 15, 2020Apr 28, 2021Aug 10, 2022Nov 22, 2023Mar 5, 2025Jun 17, 2026
Updated 4mo ago

Evaluation results

MethodLinks
BERT-MRCTraining Setting=standard2021.0183.8
State-of-the-art2022.0481.39
DEEPSTRUCTmode=w/ finetune2022.0580.8
DEEPSTRUCTEvaluation Protocol=w/ finetune2022.0580.8
Yu et al., 2020b2022.0580.5
BiaffineLSTM2022.0580.5
DEEPSTRUCTmode=multi-task2022.0580.2
DEEPSTRUCTEvaluation Protocol=multi-task2022.0580.2
BioBART LARGESize=Large2022.0479.93
KnowCoder-XEvaluation Protocol=Supervised2024.1178.97
BART LARGESize=Large2022.0478.93
GLiNEREvaluation Protocol=Supervised2026.0478.9
BioBART BASESize=Base2022.0478.43
BART BASESize=Base2022.0478.06
UniNER-7BEvaluation Protocol=Supervised2026.0477.5
KnowCoder-7BEvaluation Protocol=Supervised2026.0476.7
IEPILEEvaluation Protocol=Supervised2024.1176.66
B2NEREvaluation Protocol=Supervised2024.1176.43
TANLTraining Setting=standard2021.0176.4
TANLTraining Setting=multi-task2021.0176.4
TANL2022.0576.4
TANL2022.0576.4
TANLEvaluation Protocol=multitask2022.0576.4
B2NEREvaluation Protocol=Supervised2026.0476.4
TANLTraining Setting=multi-dataset2021.0175.9
InstructUIEEvaluation Protocol=Supervised2026.0475.7
YAYI-UIEEvaluation Protocol=Supervised2024.1175.21
Ju et al.2018.1074.7
Neural Transition-based Modelw/s=14452018.1073.9
Katiyar and Cardie2018.1073.6
BERTEvaluation Protocol=Supervised2024.1173.3
BERT-baseEvaluation Protocol=Supervised2026.0473.3
Neural Transition-based Model (w/o dropout layer)w/s=14402018.1072.7
Neural Transition-based Model (w/o char-level LSTM)w/s=15462018.1072.1
Neural Transition-based Model (w/o pre-trained embeddings)w/s=14522018.1072
Muis and Luw/s=2632018.1070.8
Finkel and Manningw/s=382018.1070.3
Lu and Rothw/s=4542018.1070.3
DiZiNERZero-shot=true2026.0460.1
DiZiNEREvaluation Protocol=Zero-shot2026.0460.1
GLADEnsemble=true2026.0458.9
MACEEnsemble=true2026.0458.4
MVEnsemble=true2026.0458
GPT-5 miniZero-shot=true2026.0456.5
GPT-5 miniEvaluation Protocol=Zero-shot, Note=supervisor model2026.0456.5
GLiNER-Lzero-shot=true2026.0455.5
Prior Best ZSZero-shot=true2026.0455.5
GLiNEREvaluation Protocol=Zero-shot2026.0455.5
gliner_medium-v2.5Evaluation Protocol=Zero-shot2026.0255.1
DSEnsemble=true2026.0454.2
UniNER-7Bzero-shot=true2026.0454.1
UniNER-7BEvaluation Protocol=Zero-shot2026.0454.1
One-shotModel=Qwen-2.5-7b, Token Cost=3852026.0652.91
BCLModel=Qwen-2.5-7b, Token Cost=5012026.0651.36
One-shotModel=Llama-3.1-8b, Token Cost=3852026.0651.29
JPT-4Bzero-shot=true2026.0450.8
BCLModel=Pixtral-12B, Token Cost=5012026.0650.65
BCLModel=Llama-3.1-8b, Token Cost=5012026.0650.15
One-shotModel=Pixtral-12B, Token Cost=3852026.0649.73
gliner_small-v2.5Evaluation Protocol=Zero-shot2026.0248.5
GuideNERModel=Pixtral-12B, Token Cost=5062026.0648.03
GuideNERModel=Qwen-2.5-7b, Token Cost=5062026.0647.43
DEEPSTRUCTmode=zero-shot2022.0547.2
DEEPSTRUCTEvaluation Protocol=zero-shot2022.0547.2
BCLModel=Qwen-2.5-3b, Token Cost=5012026.0646.98
gliner_large-v2.5Evaluation Protocol=Zero-shot2026.0246.9
One-shotModel=Qwen-2.5-3b, Token Cost=3852026.0646.78
GuideNERModel=Llama-3.1-8b, Token Cost=5062026.0642.86
ChatGPTEvaluation Protocol=Zero-shot2026.0441.6
GuideNERModel=Qwen-2.5-3b, Token Cost=5062026.0641.49
ChatIEModel=Pixtral-12B, Token Cost=9422026.0640.12
ChatIEModel=Llama-3.1-8b, Token Cost=9422026.0635.2
ChatIEModel=Qwen-2.5-3b, Token Cost=9422026.0633.32
CodeIEModel=Pixtral-12B, Token Cost=11722026.0620.62
CodeIEModel=Qwen-2.5-7b, Token Cost=11722026.0619.17
ChatIEModel=Qwen-2.5-7b, Token Cost=9422026.0610.19
CodeIEModel=Qwen-2.5-3b, Token Cost=11722026.066.59
CodeIEModel=Llama-3.1-8b, Token Cost=11722026.060