ExploitGym Launches: GPT-5.6-Sol Leads in Exploit Capabilities

Security researchers launched ExploitGym, a benchmark using 869 real-world vulnerabilities to evaluate if AI agents can create functional exploits for critical tasks like remote code execution. Results show GPT-5.6-Sol outperforming GPT-5.5 in exploit capabilities.

2026-07-25 ~ 2026-07-25 · 3 related posts