Claim and evidence Close ×
OpenAI o1 System Card (December 2024) states evaluation result ↓ Medium risk for chemical and biological threat creation: the card states its evaluations found o1 can help experts with the operational planning of reproducing a known biological threat, which meets OpenAI's medium risk threshold. The o1 System Card states that its evaluations found o1 can help experts with the operational planning of reproducing a known biological threat, which it says meets OpenAI's medium risk threshold, and that the Safety Advisory Group classified the pre-mitigation model as medium risk for CBRN. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2024-12-05 · publication Evaluated system o1, pre-mitigation and post-mitigation versions as described in the card What the report measured Chemical and biological threat creation capability, against OpenAI's own risk thresholds By what kind of method A suite of internal evaluations, with risk levels assigned by indicators and reviewed by the Safety Advisory Group The result, in the report’s words Score for o1: Medium, the same as o1-preview; the Safety Advisory Group classified the pre-mitigation model as overall medium risk, including medium risk for CBRN, and rated post-mitigation risk the same The caveats the report gives The card states that the exact performance numbers for the model used in production may vary with final parameters, system prompt and other factors, and that the model tested was a near-final post-mitigation model. Scope and limits A risk classification stated by the developer for the model version it tested, under its own framework and thresholds. It is not an independent finding, is not generalised to other models or later versions, and says nothing about whether any safeguard works. The card adds that the exact performance numbers for the production model may vary. Only the summary and classification sentences are cited; the evaluation sections themselves hold technical content and are excluded.
The evidence 02 primary source Supports the claim
OpenAI o1 System Card ↗ OpenAI · 2024-12-05
Archived copy, captured 2026-09-06: OpenAI o1 System Card ↗
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Source excerpt “Our evaluations found that o1 can help experts with the operational planning of reproducing a known biological threat, which meets our medium risk threshold.” Location in source PDF p. 19, §5.5 Chemical and Biological Threat Creation, summary line
How it was read Retrieved directly from the publisher
Machine-checked · 2026-10-30
Source details and check notes Authors OpenAI Version Page labelled Updated: December 5, 2024; includes multiple evaluation periods Version date 2024-12-05 Canonical address Open the canonical source ↗ Accessed 2026-09-17 Language English (en) Archive copy Open archived copy, captured 2026-09-06: OpenAI o1 System Card ↗ . Captured 640 days after the recorded version date. An archive copy shows only what the archive retrieved on 2026-09-06. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-09-17.Attribution OpenAI, OpenAI o1 System Card (2024-12-05). Reuse No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and minimal attributed excerpts only. Recheck terms before wider redistribution. Check notes Candidate pack passage, AI and biosecurity (research/ai-bio). The quotation (24 words) matched the text retrieved for the candidate pack on 2026-10-28 and again at admission on 2026-10-30, in a fresh retrieval whose SHA-256 equals the pack’s. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. A cross-family machine check (2026-10-30, item 23) re-read the record’s sources and found full support. No human editorial review. primary source Supports the claim
OpenAI o1 System Card ↗ OpenAI · 2024-12-05
Archived copy, captured 2026-09-06: OpenAI o1 System Card ↗
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Source excerpt “the Safety Advisory Group … classified the o1 pre-mitigation model as overall medium risk, including medium risk for persuasion and CBRN, and low risk for model autonomy and cybersecurity.” Location in source PDF p. 16, §5 Preparedness Framework Evaluations, paragraph on the Safety Advisory Group
How it was read Retrieved directly from the publisher
Machine-checked · 2026-10-30
Source details and check notes Authors OpenAI Version Page labelled Updated: December 5, 2024; includes multiple evaluation periods Version date 2024-12-05 Canonical address Open the canonical source ↗ Accessed 2026-09-17 Language English (en) Archive copy Open archived copy, captured 2026-09-06: OpenAI o1 System Card ↗ . Captured 640 days after the recorded version date. An archive copy shows only what the archive retrieved on 2026-09-06. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-09-17.Attribution OpenAI, OpenAI o1 System Card (2024-12-05). Reuse No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and minimal attributed excerpts only. Recheck terms before wider redistribution. Check notes Candidate pack passage, AI and biosecurity (research/ai-bio). The quotation (28 words) matched the text retrieved for the candidate pack on 2026-10-28 and again at admission on 2026-10-30, in a fresh retrieval whose SHA-256 equals the pack’s. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. The ellipsis stands for a reference marker in the PDF text layer. A cross-family machine check (2026-10-30, item 23) re-read the record’s sources and found full support. No human editorial review. Status and meaning Editorial status. Not reviewed by an editor . An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.
Relation. A report states the result of an evaluation it ran or commissioned, in its own words, with what was measured, by what kind of method, and the caveats the report itself gives (schema 2.22). The record is the report’s statement, not a verified finding: it says nothing about another system, a later version or real-world risk, and a null or limiting result is not evidence that no effect exists.
Date. The classification as stated in the card expression of 5 December 2024. The expression checked is the PDF served at cdn.openai.com/o1-system-card-20241205.pdf on 2026-10-28, which carries a footnote in §3 ('Scope of testing') reading 'Section added after December 5th on 12/19/2024'; the served file is therefore a later expression than the card's stated date of 5 December 2024, the card does not say what else differs, and the record keeps the stated date.
Record ID ab-ev-o1-card-cb-medium-result