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

Safety Evaluation on OLID benchmark leaderboard · SOTA2 Research

Research Benchmarks

Safety Evaluation on OLID

73F1 ScoreOpenAI

Updated 5mo ago

Evaluation Results

Method	Links
OpenAI2025.12		73
GGuard2025.12		72
LlamaGuard32025.12		55

SOTA Paper

OpenAI

A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness

Dataset

OLID

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Safety Evaluation on X (test)Safety Moderation on Wild Guard Response Safety Moderation on GuarEval Prompt Safety Moderation on Nemo-Safety Prompt Safety Moderation on Beaver Prompt