NewsMore in News→
GPT-5.5 Matches Mythos Preview in UK Cybersecurity Tests, Challenging the Hype Gap
Key Takeaways
- The UK AI Security Institute says GPT-5.5 reached a similar performance level to Mythos Preview on cyber evaluations.
- GPT-5.5 passed 71.4% of expert tasks, compared with 68.6% for Mythos Preview, within the margin of error.
- The results suggest cyber risk is rising across frontier models rather than being unique to one system.
DE
DT Editorial Team··via arstechnica.com