OpenAI

o3

• Released 16 April 2025
• Framework: Preparedness Framework version 2
• 3 statements about capability levels
• 6 independent or government tests
• 1 test by the provider
• 7 source documents

What the provider states

• Autonomy & replication · High · Stated as not crossed

  openai’s safety advisory group (sag) reviewed the results of our preparedness evaluations and determined that openai o3 and o4-mini do not reach the high threshold in any of our three tracked categories: biological and chemical capability, cybersecurity, and ai self-improvement.

  OpenAI · 16 April 2025 · Read the source
• Chemical, biological, radiological and nuclear · High · Stated as not crossed

  openai’s safety advisory group (sag) reviewed the results of our preparedness evaluations and determined that openai o3 and o4-mini do not reach the high threshold in any of our three tracked categories: biological and chemical capability, cybersecurity, and ai self-improvement.

  OpenAI · 16 April 2025 · Read the source
• Cyber · High · Stated as not crossed

  openai’s safety advisory group (sag) reviewed the results of our preparedness evaluations and determined that openai o3 and o4-mini do not reach the high threshold in any of our three tracked categories: biological and chemical capability, cybersecurity, and ai self-improvement.

  OpenAI · 16 April 2025 · Read the source

Independent and government tests

• Virology Capabilities Test · SecureBio, independent evaluator · Chemical, biological, radiological and nuclear

  since the release of vct in april 2025, the accuracy of the top-performing model on the benchmark has increased by ~12 percentage points (o3: 42.0%; gpt-5.6 sol: 53.9%).

  SecureBio · 11 September 2026 · Read the source
• benchtop DNA synthesis agent evaluation · RAND, independent evaluator · Chemical, biological, radiological and nuclear

  in our early testing, an o3-driven agent created a set of dna sequences encoding egfp that was successfully assembled, amplified, cloned, and expressed by our research partners in a laboratory.

  RAND (CAST / Project Canary) · 3 February 2026 · Read the source
• denial of requests to aid in laboratory tasks · RAND, independent evaluator · Misuse & jailbreak

  claude opus 4, opus 4.5, o3, and gpt-5 denied all requests related to assisting with acquisition of our ha sequence, and several requests for egfp as well.

  RAND (CAST / Project Canary) · 3 February 2026 · Read the source
• egfp task · RAND, independent evaluator · Chemical, biological, radiological and nuclear

  o3 refused 6/10 requests for egfp, so it generated significantly fewer performance data than many of our other models.

  RAND (CAST / Project Canary) · 3 February 2026 · Read the source
• physical validation of o3-designed DNA sequences and o3-generated laboratory protocol · RAND, independent evaluator · Chemical, biological, radiological and nuclear

  the validation experiment showed that o3-designed dna sequences could be assembled into a functional egfp protein and that the o3-generated protocol was accurate.

  RAND (CAST / Project Canary) · 3 February 2026 · Read the source
• physical validation proof-of-concept · RAND, independent evaluator · Chemical, biological, radiological and nuclear

  they then successfully followed o3’s protocol, with the minor variations described in appendix c, to assemble those segments into a valid egfp gene, insert that gene into a plasmid, and express it to confirm that the protein was functional.

  RAND (CAST / Project Canary) · 3 February 2026 · Read the source

The provider's own tests

• preparedness evaluations · The provider · Chemical, biological, radiological and nuclear

  openai’s safety advisory group (sag) reviewed the results of our preparedness evaluations and determined that openai o3 and o4-mini do not reach the high threshold in any of our three tracked categories: biological and chemical capability, cybersecurity, and ai self-improvement.

  OpenAI · 16 April 2025 · Read the source

No document we read states: a safeguard. No incident on record names this version.

Some documents we hold are stored in lower case only, so their quotes are shown in lower case. The source link opens the original.

Compare with other versions