SOTA Automated Essay Scoring on ASAP 1.0 (test) and PapersWithCode

Method
HA-LSTM+SST+DAT 2022.05	0.836	0.73	0.732	0.822	0.835	0.832	0.821	0.718	0.79
BERT-DOC-TOK-SEG 2022.05	0.836	0.695	0.7	0.815	0.812	0.816	0.838	0.744	0.782
Tran-BERT-MS-ML-R 2022.05	0.834	0.716	0.714	0.812	0.813	0.836	0.839	0.766	0.791
SKIPFLOW LSTM 2017.11	0.832	0.684	0.695	0.788	0.815	0.81	0.8	0.697	0.764
Tay et al. 2021.02	0.832	0.684	0.694	0.788	0.815	0.81	0.8	0.697	0.764
SKIPFLOW LSTM 2022.05	0.832	0.684	0.695	0.788	0.815	0.81	0.8	0.697	0.764
MTL-BiLSTM 2021.02	0.831	0.689	0.687	0.798	0.8	0.813	0.795	0.699	0.764
SKIPFLOW LSTM 2017.11	0.83	0.678	0.677	0.778	0.795	0.807	0.79	0.67	0.753
MTL-LSTM 2021.02	0.83	0.667	0.644	0.786	0.782	0.806	0.791	0.679	0.748
SKIPFLOW LSTM 2022.05	0.83	0.678	0.677	0.778	0.795	0.807	0.79	0.67	0.753
BERT+SST+DAT 2022.05	0.824	0.699	0.726	0.859	0.822	0.828	0.84	0.726	0.791
Hierarchical LSTM-CNN-Attention 2022.05	0.822	0.682	0.672	0.814	0.803	0.811	0.801	0.705	0.764
CNN + LSTM 2022.05	0.821	0.688	0.694	0.805	0.807	0.819	0.808	0.644	0.761
STL-BiLSTM 2021.02	0.818	0.658	0.653	0.78	0.789	0.803	0.786	0.697	0.748
R2BERT 2022.05	0.817	0.719	0.698	0.845	0.841	0.847	0.839	0.744	0.794
STL-LSTM 2021.02	0.813	0.66	0.661	0.79	0.798	0.807	0.792	0.678	0.75
Kernel 2021.02	0.804	0.687	0.704	0.743	0.799	0.753	0.698	0.552	0.717
ML-LSTM 2017.11	0.8	0.63	0.667	0.687	0.774	0.612	0.728	0.545	0.676
BI-LSTM 2017.11	0.794	0.625	0.665	0.674	0.776	0.613	0.679	0.506	0.667
RNN 2017.11	0.793	0.667	0.591	0.752	0.713	0.77	0.784	0.576	0.706
ATT-LSTM 2017.11	0.793	0.66	0.664	0.768	0.8	0.789	0.788	0.637	0.737
ML-LSTM 2017.11	0.793	0.682	0.643	0.769	0.777	0.772	0.789	0.683	0.739
GRU 2017.11	0.792	0.666	0.592	0.757	0.727	0.753	0.779	0.649	0.714
LSTM 2017.11	0.792	0.676	0.583	0.745	0.725	0.765	0.78	0.651	0.715
CNN 2017.11	0.789	0.674	0.59	0.742	0.726	0.757	0.771	0.614	0.708
SKIPFLOW CNN 2017.11	0.782	0.657	0.666	0.727	0.781	0.756	0.757	0.44	0.696
EASE 2017.11	0.781	0.63	0.621	0.749	0.782	0.771	0.727	0.534	0.699
EASE 2022.05	0.781	0.621	0.63	0.749	0.782	0.771	0.727	0.534	0.699
SKIPFLOW CNN 2017.11	0.78	0.62	0.628	0.719	0.775	0.721	0.729	0.409	0.673
Dilated LSTM With RL 2022.05	0.776	0.659	0.688	0.778	0.805	0.791	0.76	0.545	0.724
EASE 2017.11	0.761	0.621	0.606	0.742	0.784	0.775	0.73	0.617	0.705
EASE 2022.05	0.761	0.606	0.621	0.742	0.784	0.775	0.73	0.617	0.705
ML-LSTM 2017.11	0.7	0.554	0.641	0.753	0.78	0.764	0.752	0.558	0.688
Llama-2-7b-chat-hf 2025.12	0.665	0.663	0.667	0.695	0.701	0.656	0.558	0.614	0.652
Qwen3-8B 2025.12	0.664	0.679	0.676	0.718	0.701	0.678	0.521	0.598	0.654
PMAES 2025.12	0.656	0.555	0.615	0.623	0.634	0.593	0.406	0.533	0.566
Qwen3-1.7B 2025.12	0.649	0.65	0.629	0.672	0.693	0.645	0.517	0.564	0.627
PLAES 2025.12	0.648	0.563	0.604	0.623	0.634	0.593	0.403	0.533	0.575
DeepSeek-R1-Distill-Llama-8B 2025.12	0.648	0.642	0.651	0.694	0.7	0.657	0.478	0.578	0.631
ProTACT 2025.12	0.647	0.587	0.623	0.632	0.674	0.574	0.446	0.541	0.592
Qwen3-4B 2025.12	0.645	0.663	0.651	0.696	0.707	0.658	0.456	0.565	0.63
KAES 2025.12	0.623	0.611	0.619	0.636	0.685	0.593	0.433	0.577	0.597
CTS 2025.12	0.62	0.555	0.631	0.62	0.613	0.548	0.384	0.504	0.56
PAES 2025.12	0.615	0.582	0.57	0.606	0.634	0.545	0.356	0.447	0.543
Qwen3-0.6B 2025.12	0.61	0.619	0.598	0.662	0.681	0.621	0.57	0.61	0.622
GRU 2017.11	0.608	0.515	0.593	0.737	0.725	0.738	0.733	0.515	0.646
RNN 2017.11	0.597	0.488	0.603	0.745	0.74	0.759	0.741	0.489	0.645
LSTM 2017.11	0.583	0.523	0.591	0.757	0.737	0.756	0.706	0.514	0.646
RNN 2017.11	0.521	0.025	0.001	0.001	0.001	0.001	0.165	0.094	0.102
GRU 2017.11	0.521	0.265	0.274	0.678	0.441	0.563	0.42	0.182	0.418
LSTM 2017.11	0.319	0.2	0.317	0.69	0.389	0.522	0.423	0.189	0.467

HA-LSTM+SST+DAT

2022.05

0.836

0.73

0.732

0.822

0.835

0.832

0.821

0.718

0.79

BERT-DOC-TOK-SEG

2022.05

0.836

0.695

0.7

0.815

0.812

0.816

0.838

0.744

0.782

Tran-BERT-MS-ML-R

2022.05

0.834

0.716

0.714

0.812

0.813

0.836

0.839

0.766

0.791

SKIPFLOW LSTM

2017.11

0.832

0.684

0.695

0.788

0.815

0.81

0.8

0.697

0.764

Tay et al.

2021.02

0.832

0.684

0.694

0.788

0.815

0.81

0.8

0.697

0.764

SKIPFLOW LSTM

2022.05

0.832

0.684

0.695

0.788

0.815

0.81

0.8

0.697

0.764

MTL-BiLSTM

2021.02

0.831

0.689

0.687

0.798

0.8

0.813

0.795

0.699

0.764

SKIPFLOW LSTM

2017.11

0.83

0.678

0.677

0.778

0.795

0.807

0.79

0.67

0.753

MTL-LSTM

2021.02

0.83

0.667

0.644

0.786

0.782

0.806

0.791

0.679

0.748

SKIPFLOW LSTM

2022.05

0.83

0.678

0.677

0.778

0.795

0.807

0.79

0.67

0.753

BERT+SST+DAT

2022.05

0.824

0.699

0.726

0.859

0.822

0.828

0.84

0.726

0.791

Hierarchical LSTM-CNN-Attention

2022.05

0.822

0.682

0.672

0.814

0.803

0.811

0.801

0.705

0.764

CNN + LSTM

2022.05

0.821

0.688

0.694

0.805

0.807

0.819

0.808

0.644

0.761

STL-BiLSTM

2021.02

0.818

0.658

0.653

0.78

0.789

0.803

0.786

0.697

0.748

R2BERT

2022.05

0.817

0.719

0.698

0.845

0.841

0.847

0.839

0.744

0.794

STL-LSTM

2021.02

0.813

0.66

0.661

0.79

0.798

0.807

0.792

0.678

0.75

Kernel

2021.02

0.804

0.687

0.704

0.743

0.799

0.753

0.698

0.552

0.717

ML-LSTM

2017.11

0.8

0.63

0.667

0.687

0.774

0.612

0.728

0.545

0.676

BI-LSTM

2017.11

0.794

0.625

0.665

0.674

0.776

0.613

0.679

0.506

0.667

RNN

2017.11

0.793

0.667

0.591

0.752

0.713

0.77

0.784

0.576

0.706

ATT-LSTM

2017.11

0.793

0.66

0.664

0.768

0.8

0.789

0.788

0.637

0.737

ML-LSTM

2017.11

0.793

0.682

0.643

0.769

0.777

0.772

0.789

0.683

0.739

GRU

2017.11

0.792

0.666

0.592

0.757

0.727

0.753

0.779

0.649

0.714

LSTM

2017.11

0.792

0.676

0.583

0.745

0.725

0.765

0.78

0.651

0.715

CNN

2017.11

0.789

0.674

0.59

0.742

0.726

0.757

0.771

0.614

0.708

SKIPFLOW CNN

2017.11

0.782

0.657

0.666

0.727

0.781

0.756

0.757

0.44

0.696

EASE

2017.11

0.781

0.63

0.621

0.749

0.782

0.771

0.727

0.534

0.699

EASE

2022.05

0.781

0.621

0.63

0.749

0.782

0.771

0.727

0.534

0.699

SKIPFLOW CNN

2017.11

0.78

0.62

0.628

0.719

0.775

0.721

0.729

0.409

0.673

Dilated LSTM With RL

2022.05

0.776

0.659

0.688

0.778

0.805

0.791

0.76

0.545

0.724

EASE

2017.11

0.761

0.621

0.606

0.742

0.784

0.775

0.73

0.617

0.705

EASE

2022.05

0.761

0.606

0.621

0.742

0.784

0.775

0.73

0.617

0.705

ML-LSTM

2017.11

0.7

0.554

0.641

0.753

0.78

0.764

0.752

0.558

0.688

Llama-2-7b-chat-hf

2025.12

0.665

0.663

0.667

0.695

0.701

0.656

0.558

0.614

0.652

Qwen3-8B

2025.12

0.664

0.679

0.676

0.718

0.701

0.678

0.521

0.598

0.654

PMAES

2025.12

0.656

0.555

0.615

0.623

0.634

0.593

0.406

0.533

0.566

Qwen3-1.7B

2025.12

0.649

0.65

0.629

0.672

0.693

0.645

0.517

0.564

0.627

PLAES

2025.12

0.648

0.563

0.604

0.623

0.634

0.593

0.403

0.533

0.575

DeepSeek-R1-Distill-Llama-8B

2025.12

0.648

0.642

0.651

0.694

0.7

0.657

0.478

0.578

0.631

ProTACT

2025.12

0.647

0.587

0.623

0.632

0.674

0.574

0.446

0.541

0.592

Qwen3-4B

2025.12

0.645

0.663

0.651

0.696

0.707

0.658

0.456

0.565

0.63

KAES

2025.12

0.623

0.611

0.619

0.636

0.685

0.593

0.433

0.577

0.597

CTS

2025.12

0.62

0.555

0.631

0.62

0.613

0.548

0.384

0.504

0.56

PAES

2025.12

0.615

0.582

0.57

0.606

0.634

0.545

0.356

0.447

0.543

Qwen3-0.6B

2025.12

0.61

0.619

0.598

0.662

0.681

0.621

0.57

0.61

0.622

GRU

2017.11

0.608

0.515

0.593

0.737

0.725

0.738

0.733

0.515

0.646

RNN

2017.11

0.597

0.488

0.603

0.745

0.74

0.759

0.741

0.489

0.645

LSTM

2017.11

0.583

0.523

0.591

0.757

0.737

0.756

0.706

0.514

0.646

RNN

2017.11

0.521

0.025

0.001

0.165

0.094

0.102

GRU

2017.11

0.521

0.265

0.274

0.678

0.441

0.563

0.42

0.182

0.418

LSTM

2017.11

0.319

0.2

0.317

0.69

0.389

0.522

0.423

0.189

0.467

Automated Essay Scoring on ASAP 1.0 (test)

Evaluation Results