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

HotpotQA dataset and benchmarks – Page 9 · SOTA2 Research

Research Datasets

HotpotQA

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Multi-hop Question Answering

HotpotQA N=1,000

73Judge EM

16

Multi-hop Question Answering

HotpotQA 1600 documents

55.76F1

16

Multi-hop Question Answering

HotpotQA 800 documents

55.46F1 Score

16

Multi-hop Question Answering

HotpotQA 400 documents

61.46F1 Score

16

HotpotQA

47QA-F1

16

Multi-hop Question Answering

HotpotQA subset of 100 questions

71EM

16

Question Answering

HotpotQA In-distribution (test)

30.9Accuracy

15

HotpotQA

45Accuracy

15

Multi-Hop Question Answering

HotpotQA

38.9HotpotQA Score

15

Multi-hop Retrieval

HotPotQA

0.065Latency (s)

15

Question Answering

HotpotQA

0.188Mean Per-Step Regret

15

Question Answering

HotpotQA

69.1F1 Score

15

Multi-hop Question Answering

HotpotQA

88Accuracy

15

HotpotQA

0.9Kendall's Tau

15

Multi-Hop Question Answering

HotpotQA in-domain (val test)

49.9Exact Match (EM)

15

Question Answering

HotpotQA

59.93F1 Score

15

Answer extraction and supporting sentence prediction

HotpotQA fullwiki (dev)

66.56Answer EM

15

HotpotQA

5Target@5

14

HotpotQA (test)

45.2Exact Match (EM)

14

MAS Test-Time Scaling

HotpotQA

57Accuracy

14

Question Answering

HotpotQA

65.6Containment Accuracy

14

Question Answering

HotPotQA

73.4F1 Score

14

Hallucination Detection

HotpotQA

80.3Accuracy

14

Multi-hop Question Answering

HotpotQA

52Exact Match Accuracy

14

Monolingual Question Answering

HOTPOTQA

44.14fEM

14

Page 9 of 27

Popular tasks

Question Answering Multi-hop Question Answering Retrieval Open-domain Question Answering Multi-hop Reasoning

Follow for updates

Join SOTA2 Contact