GPT-5 System Card
As dated August 13, 2025 on its cover. Date printed on the card's cover.
- Issued by
- OpenAI
- Authors credited
- No authorship claim recorded yet. The source record lists OpenAI.
- Dates
- Published 2025-08-13 issue evidence
Date printed on the card's cover.
- Exact source
- GPT-5 System Card OpenAI · publication date unknown · Retrieved for the candidate pack on 2026-10-28 (SHA-256 f9f9c72d08cba81dcbb189129119357c8c32eca4e0b16c813aca386aed6b0459). PDF dated August 13, 2025 on its cover, as served on 2026-10-28. Retrieved again at admission on 2026-10-30 (SHA-256 f9f9c72d08cba81dcbb189129119357c8c32eca4e0b16c813aca386aed6b0459, the same bytes).
Appears in
No collection holds a record about this document yet.
Versions
openai-gpt5-system-card: 1 recorded version, oldest first, published by OpenAI. A version is shown as replacing another only where a record says so. Date order alone never implies it.
- 2025-08-13 · publishedAs dated August 13, 2025 on its cover (this version)
This version
Earliest version recorded here; no replacement is recorded.
Issue and authorship records
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.
Other recorded relations
- states evaluation resultThe GPT-5 System Card states that OpenAI decided to treat gpt-5-thinking as High capability in the Biological and Chemical domain under its Preparedness Framework, activating the associated safeguards, while stating that it does not have definitive evidence that the model could meaningfully help a novice to create severe biological harm.2025-08-13 · publication · Stated in source · Supported Inspect claim & evidence ↗
- states evaluation resultThe GPT-5 System Card states that the UK AI Security Institute's safeguards team identified multiple model-level jailbreaks that overcome gpt-5-thinking's built-in refusal logic without degrading model capabilities, and that one of them evades all layers of mitigations and is being patched.2025-08-13 · publication · Stated in source · Supported Inspect claim & evidence ↗