Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Machine Reading Comprehension research benchmarks – Page 3 · SOTA2 Research

Machine Reading Comprehension

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

SQuAD AddOneSent

60.9EM

7

Feb 26, 2026

53EM

7

Feb 26, 2026

81.05F1 Score

6

Jun 9, 2026

96.88Score

6

Apr 30, 2026

RoBERTa-Large + MUPPET

89.4F1

6

Feb 26, 2026

DuReader 1.0 (test)

49.39BLEU-4

6

Feb 26, 2026

AddOneSent (adversarial)

72.3F1 Score

6

Feb 26, 2026

AddSent (adversarial)

60.1F1 Score

6

Feb 26, 2026

MultiRC SuperGLUE (test)

27.2EM

5

Feb 26, 2026

ROCStories (test)

GPT+Strategies (2x)

0.883Accuracy

5

Feb 26, 2026

SemEval Task 11 2018 (test)

GPT+Strategies (2x)

0.895Accuracy

5

Feb 26, 2026

OpenBookQA (test)

GPT+Strategies (2x)

55.8Accuracy

5

Feb 26, 2026

ARC Challenge (test)

GPT+Strategies (2x)

42.3Accuracy

5

Feb 26, 2026

ARC Easy (test)

GPT+Strategies (2x)

68.9Accuracy

5

Feb 26, 2026

DuReader (test)

56.1BLEU-4

5

Feb 26, 2026

TriviaQA Wikipedia Full (dev)

0.511EM

5

Feb 26, 2026

6.9ROUGE-L

4

Feb 26, 2026

10.2ROUGE-L

4

Feb 26, 2026

11.1ROUGE-L

4

Feb 26, 2026

11.5ROUGE-L

4

Feb 26, 2026

44.7ROUGE-L

4

Feb 26, 2026

MLQA Target - English v1.0 (test)

26.59EM (German)

4

Feb 26, 2026

MLQA English - Target v1.0 (test)

31.28German EM

4

Feb 26, 2026

RACENum (unsupervised)

52.53Accuracy (RACE-M)

4

Feb 26, 2026

BioMRC Tiny (test)

MLP-BASED WEIGHTING MODEL (OURS)

96.66Accuracy

4

Feb 26, 2026

Page 3 of 4

Popular datasets

Belebele SQuAD CMRC RACE CJRC

Follow for updates

Join SOTA2 Contact