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

CommonsenseQA dataset and benchmarks – Page 3 · SOTA2 Research

Research Datasets

CommonsenseQA

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Counterfactual Subset-Utility Evaluation

CommonsenseQA

0.26Spearman Correlation ($ ho$)

4

Robustness Evaluation

CommonsenseQA

79.07VAcc

4

Question Answering

CommonSenseQA

78.6Accuracy

3

Commonsense Reasoning

CommonsenseQA

83.9Pass@1

3

Commonsense reasoning

CommonsenseQA

81.9Accuracy

3

Downstream accuracy extrapolation

CommonsenseQA

0.004RMSE

3

Logic Reasoning

CommonsenseQA

69.8Pass@1

3

Commonsense Reasoning

CommonsenseQA

57Accuracy

2

Multiple Choice Question Answering

CommonsenseQA 7-shot (test)

81.33Accuracy

2

CommonsenseQA

65.8Accuracy

2

Commonsense Question Answering

COMMONSENSEQA

75ACC

2

Multiple Choice Question Answering

CommonsenseQA (CSQA)

2.345BPC

2

Multiple-choice Question Answering

CommonsenseQA

68.3Accuracy

2

Page 3 of 3

Popular tasks

Commonsense Reasoning Question Answering Commonsense Question Answering Multiple-choice Question Answering Jailbreak Attack

Follow for updates

Join SOTA2 Contact