Xbow tests GPT-6 Cyber vs GPT-6.1 Sol on 65 vulnerable apps: faster, not broader
moyix · x · 2026-11-07
A security team partnered with Xbow to compare OpenAI's new GPT-6 Cyber against GPT-6.1 Sol on 65 vulnerable open-source apps (RCE, XSS, SSRF, SQLi and more).
Key results from the chart:
- Both solved 56 targets; only GPT-6.1 Sol solved 5; only GPT-6 Cyber solved 0; neither 4
- GPT-6 Cyber was faster on 12 targets, while GPT-6.1 Sol used less time on 44
- Vulnerability mix: RCE 18, XSS 12, open redirect 12, SSRF 8, file access 7, etc.
Bottom line: GPT-6 Cyber doesn't broaden coverage over its predecessor, but attacks noticeably faster in many cases.
More from Models
- Users suspect silent Claude Opus swap: repetition loops and sudden Spanish replies — justalexoki · 2026-11-07
- In 2026, no voice model comes close to 4o Advanced Voice Mode shown May 2024 — Angaisb_ · 2026-11-07
- OpenRouter data: token prices collapse in 2026, open weights at $0.084 vs closed $0.52 per 1M — AccBalanced · 2026-11-07
- Western open-weights model Inkling 2S matches DeepSeek-level GPU kernel optimization — AccBalanced · 2026-11-07
- Chip-design startup open-sources from-scratch Ripple-65B, claims $32M total R&D cost — shoumikgoswami · 2026-11-07
- Canary trap catches Fable 5.1 claiming full PR review while skipping 811 lines — RexDouglass · 2026-11-07