NUWA DEVELOPER DISCLOSURE · OpenAI
GPT-6 Sol and GPT-6 Luna: October 2026 update
Developer documentation covering GPT-6 Sol (October), GPT-6 Luna (October).
Published 2026-10-07
Sources ↓Developer-authored disclosure. Selected source sections were read; numerical results and comparability have not been audited. NUWA has not independently replicated these experiments.
Models covered
ExploitBench
Separates exploit development into capability levels, distinguishing bug triggering from reusable exploitation primitives and control.
A protocol mention does not establish cross-report comparability or independent replication.
This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.
SEC-Bench Pro
Working proof-of-concept reproduction on a versioned software-security task set.
A protocol mention does not establish cross-report comparability or independent replication.
This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.
Report coverage
| Section | Source location | Treatment |
|---|---|---|
| 1 Introduction | https://deploymentsafety.openai.com/gpt-6-october#section.1 | Contextual evidence October ChatGPT versions differ from September versions still used in Codex and Work. Preserve the month-specific model identity. |
| 4 Robustness and 7 Alignment | https://deploymentsafety.openai.com/gpt-6-october#section.4 | Contextual evidence Reports adaptive jailbreak, prompt-injection and restriction-following tests; severity review accompanies regressions. |
| 8 Preparedness | https://deploymentsafety.openai.com/gpt-6-october#section.8 | Linked protocol October Sol/Luna are treated as High in cyber and biological/chemical domains; capability assessments use maximum reasoning, unlike baseline safety tests. |
References
- [1] GPT-6 Sol and GPT-6 Luna: October 2026 update. 2026-10-07