OpenAI Daybreak cyber defense evaluations: Results as Published

Completion rates on defensive security work, used to check that cyber safeguards do not block legitimate defenders: vulnerability discovery and analysis, vulnerability patching, proof-of-concept exploit creation and cyber red-teaming, plus the separate Advanced Cybersecurity Completion Rate on arbitrary cyber requests. Models are compared without Trusted Access and with the Daybreak Blue or Daybreak Red access programmes. Higher values mean more tasks completed.

Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.