← Back to feed
general Infosecurity Magazine

Infosecurity Europe: Mythos Outperforms GPT5.5 on Google Chrome Vulnerability Exploits, Says New Benchmark

Infosecurity Magazine Google

A Bugcrowd researcher has unveiled ExploitBench, an independent benchmark of AI models for vulnerability exploitation

Read the full story Infosecurity Magazine →

Related Coverage

general Here’s what Anthropic found when it turned Mythos loose on encryption algorithms Cyberscoop · Jul 28 general OpenAI models used Artifactory zero-days to escape to the internet BleepingComputer · Jul 28 general IPMI bug in BMCs found after 22 years, exposes 24,000-plus servers SC Media · Jul 28