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

OpenBookQA dataset and benchmarks – Page 4 · SOTA2 Research

Research Datasets

OpenBookQA

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Question Answering

OpenBookQA

51.8Accuracy

4

Question Answering

OpenBookQA

47.9Accuracy

4

Question Answering

OpenBookQA

77.2Normalized Log Accuracy

4

Multiple Choice Question Answering

OpenbookQA 30% Label Noise (train)

5.104NLL

3

Multiple Choice Question Answering

OpenbookQA 20% Label Noise (train)

5.09NLL

3

Downstream accuracy extrapolation

OpenBookQA

0RMSE

3

Question Answering

OpenBookQA

34.2Accuracy

3

Question Answering

OpenBookQA

72.5Accuracy

3

Logical Reasoning

OpenBookQA (test)

88.8Accuracy (OpenBookQA Test)

2

Question Answering

OpenBookQA

28E*S Score

2

Question Answering

OpenBookQA

45OpenBookQA Score

2

Audio-language generation

OpenBookQA VoiceBench

38.5Score

2

Question Answering

OpenBookQA

45.4Accuracy

2

OpenBookQA 10-shot

0.696Normalized Log Accuracy

2

Question Answering

OpenBookQA

48.47Accuracy

2

Question Answering

OpenBookQA (train)

—Accuracy

0

Page 4 of 4

Popular tasks

Question Answering Open-Book Question Answering Multiple-choice Question Answering Commonsense Reasoning Commonsense Question Answering

Follow for updates

Join SOTA2 Contact