ChatGPT Agent System Card
As dated July 17, 2025 on its cover. Date printed on the card's cover; the dataset already holds the source record source-openai-chatgpt-agent-system-card for this PDF but no document entity.
- Issued by
- OpenAI
- Authors credited
- No authorship claim recorded yet. The source record lists OpenAI.
- Dates
- Published 2025-07-17 issue evidence
Date printed on the card's cover; the dataset already holds the source record source-openai-chatgpt-agent-system-card for this PDF but no document entity.
- Exact source
- ChatGPT Agent System Card OpenAI · published 2025-07-17 · System card dated 17 July 2025 on its cover. The quoted sentence and its page match the PDF served on 2026-10-04 and the Internet Archive capture of 2025-07-17; the two copies differ only in chart labels.Archived copy, captured 2025-07-17: ChatGPT Agent System Card. Captured on the recorded publication date. An archive copy shows only what the archive retrieved on 2025-07-17. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-10-04.
Appears in
No collection holds a record about this document yet.
Versions
openai-chatgpt-agent-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.
- 2025-07-17 · publishedAs dated July 17, 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.
Reports evaluation of · 1
Evaluation categories named in the document, not findings that a system has the property.
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. A missing record does not show that the relation does not exist.
Other recorded relations
- states evaluation resultThe ChatGPT Agent System Card states that OpenAI invited seven experts with biosafety and biosecurity backgrounds to spend three to five hours with a helpful-only version of the model and to score it in a survey, and that experts noted an average success rate of about 7.7 on a scale of 1 to 10 on the tasks they attempted.2025-07-17 · publication · Stated in source · Supported Inspect claim & evidence ↗
- states evaluation resultThe ChatGPT Agent System Card states that OpenAI decided to treat the launch 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 and has taken a precautionary approach.2025-07-17 · publication · Stated in source · Supported Inspect claim & evidence ↗