Sakana AI’s Fugu-Cyber update tops real-world security benchmarks

SakanaAILabs · x · 2026-07-21

Sakana AI says its new **Fugu-Cyber** update for the Fugu orchestration model reaches state-of-the-art results on real-world security benchmarks. - The company says it matches cyber-focused frontier models such as **GPT-5.5-Cyber** and **Mythos Preview**. - In the attached charts, Fugu-Cyber scores **86.9** on **CyberGym** versus **85.6** for GPT-5.5-Cyber and **83.1** for Mythos Preview. - On **CTI-REALM**, it scores **72.1**, ahead of **GPT-5.5** at **67.3** and **Mythos Preview** at **68.5**.

Related event: Sakana AI Launches Fugu-Cyber Model Achieving SOTA in Security(3 posts)→

Original post →

More from Models

Models channel →