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 103 · SOTA2 Research

Question Answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

33Log Accuracy

4

Mar 18, 2026

SQuAD (held-out)

GPT-2 small (fine-tuned)

50.9Exact Match (EM)

4

Mar 13, 2026

72.4Accuracy

4

Mar 10, 2026

5.46Inference Time (seconds)

4

Mar 9, 2026

7.27Inference Time (s)

4

Mar 9, 2026

10.8Inference Time (s)

4

Mar 9, 2026

88.1ARC-C Score

4

Mar 6, 2026

TruthfulQA MC2 0-shot (test)

64.27Accuracy

4

Mar 6, 2026

30.5EM

4

Mar 4, 2026

42.2Score

4

Mar 4, 2026

27.24Raw Score

4

Mar 4, 2026

Combined MedQA (Medical) and CaseHOLD (Legal) (test)

DeepSieve (Naive RAG)

24EM

4

Mar 4, 2026

QA Benchmark Suite Aggregate

0.331Average Score

4

Feb 26, 2026

46.8Accuracy (GPT-2-Small)

4

Feb 26, 2026

21.8Accuracy (GPT-2-Small)

4

Feb 26, 2026

17.8Accuracy (GPT-2-Small)

4

Feb 26, 2026

43Accuracy (GPT-2-Small)

4

Feb 26, 2026

PubMedQA official (val)

93.33F1 Score

4

Feb 26, 2026

Chinese-SimpleQA

77.6EM

4

Feb 26, 2026

Qwen3-Embedding (8B)

1.9Indexing Time (min)

4

Feb 26, 2026

TriviaQA (test)

0.87LLM Judge Score

4

Feb 26, 2026

MultiExpertQA All (test)

0.79F1 Score

4

Feb 26, 2026

52.8ANLL

4

Feb 26, 2026

19.7ANLL

4

Feb 26, 2026

55.2Accuracy

4

Feb 26, 2026

Page 103 of 122

Popular datasets

HotpotQA TriviaQA ARC NQ SQuAD

Follow for updates

Join SOTA2 Contact