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

OpenAI Moderation dataset and benchmarks · SOTA2 Research

Research Datasets

OpenAI Moderation

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Harmfulness Detection

OpenAI Moderation

92.9Macro F1 Score

59

Safety Classification

OpenAI-moderation (test)

74.88Accuracy

23

Safety Classification

OpenAI Moderation

81.4F1 Score

18

Prompt Classification

OpenAI Moderation Text Prompt

88.89F1 Score

14

Unsafe content categorization

OpenAI Moderation

88.35Accuracy

9

Multi-label Safety Categorization

OpenAI Moderation

47.67Macro Accuracy

4

Out-of-Taxonomy Risk Detection

OpenAI Moderation

67.92Out-of-Taxonomy F1

4

OOD safety category inference (Stage 2)

OpenAI Moderation

36.45Mean Reward

4

OpenAI’s Moderation

100Bypass Rate

1

Popular tasks

Safety Classification Jailbreaking Prompt Classification OOD safety category inference (Stage 2)Out-of-Taxonomy Risk Detection

Follow for updates

Join SOTA2 Contact