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 73 · SOTA2 Research

Question Answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

0.521ECE

8

Feb 26, 2026

0.416ECE

8

Feb 26, 2026

0.45ECE

8

Feb 26, 2026

0.217ECE

8

Feb 26, 2026

46.7Sycophancy Rate

8

Feb 26, 2026

44.4Sycophancy Rate

8

Feb 26, 2026

HELMET RAG subset

81.1HotpotQA Accuracy

8

Feb 26, 2026

Natural Questions (NQ)

2.19Speedup

8

Feb 26, 2026

XQuAD English Distractor I - (X), Q(X & EN) (Avg)

Bloom-7.1B (Selective SFT)

98.23Language Consistency

8

Feb 26, 2026

XQuAD Code Switched P, I - (EN), Q(X) (Avg)

Qwen-3-32B (Full scope SFT)

100Language Consistency

8

Feb 26, 2026

XQuAD Monolingual P, I, Q - (X) (Avg)

Qwen-3-32B (Full scope SFT)

100Language Consistency

8

Feb 26, 2026

83.17Accuracy

8

Feb 26, 2026

MAPLE-QA Qwen2.5-Omni-3B (eval)

57.24V Score

8

Feb 26, 2026

35.2OpenBookQA Accuracy (Before Attack)

8

Feb 26, 2026

BoolQ SuperGLUE (test)

63.83Accuracy (Test)

8

Feb 26, 2026

Typical Sampling + DFD

45.17Truth & Info Score

8

Feb 26, 2026

Typical + DFD (MPT-7B)

59.6Factuality

8

Feb 26, 2026

Typical + DFD (MPT-7B)

29.62Factuality

8

Feb 26, 2026

Knowledge-based Benchmarks Vietnamese

30.77ARC Score

8

Feb 26, 2026

Knowledge-based Benchmarks Arabic

27.03ARC Score

8

Feb 26, 2026

Knowledge-based Benchmarks German

30.8ARC Score

8

Feb 26, 2026

0.565Precision@1

8

Feb 26, 2026

Oracle Retriever

84.8ROUGE-L

8

Feb 26, 2026

4.82Helpfulness

8

Feb 26, 2026

Commonsense Reasoning Suite (ARC-e, ARC-c, BoolQ, OBQA, PIQA) (test)

77.7ARC-e

8

Feb 26, 2026

Page 73 of 122

Popular datasets

HotpotQA TriviaQA ARC NQ SQuAD

Follow for updates

Join SOTA2 Contact