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

Question Answering research benchmarks – Page 86 · SOTA2 Research

Question Answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Chinese Judge Case

68Accuracy

6

Feb 26, 2026

46.1Accuracy

6

Feb 26, 2026

86.3Accuracy

6

May 12, 2026

66.4Acc

6

Feb 26, 2026

ARC-C EU20 (test)

34.56Accuracy

6

Feb 26, 2026

55.68Accuracy

6

Feb 26, 2026

53.54Accuracy

6

Feb 26, 2026

83.84Pass@20

6

Feb 26, 2026

83.26Pass@20

6

Feb 26, 2026

LLM-QA Llama-3.1-8B-based (test)

38.34Accuracy

6

Feb 26, 2026

Attention Rectification

87.3Reverse Accuracy

6

Feb 26, 2026

Attention Rectification

74.5Reverse QA Score

6

Feb 26, 2026

Attention Rectification

67.6Reverse Score

6

Feb 26, 2026

Entity-Aware Contrastive Learning

89.89Adv. EM

6

Feb 26, 2026

NO-BoolQ NLEBench (test)

0.632Accuracy

6

Feb 26, 2026

65Accuracy

6

Feb 26, 2026

56.1BLEU-1

6

Feb 26, 2026

Materials held-out (test)

GAG (Gen+Adj+Mat)

71.36BERTScore

6

Feb 26, 2026

Urdu Question Answering (Non-Clean)

0.17ROUGE-L

6

Feb 26, 2026

Urdu Question Answering (QA-C) (Clean)

47ROUGE-L

6

Feb 26, 2026

Standard NLP Benchmarks

63.5Exact Match

6

Feb 26, 2026

62.82Precision

6

Feb 26, 2026

LCLF-QA 1.0 (test)

67.98Recall

6

Feb 26, 2026

0.788Accuracy

6

Feb 26, 2026

TOKENSAR + CoT-UQ

66.91AUROC

6

Feb 26, 2026

Page 86 of 122

Popular datasets

HotpotQA TriviaQA ARC NQ SQuAD

Follow for updates

Join SOTA2 Contact