OpenAI image input safety evaluations: Results as Published

Safe-completion rates on disallowed requests that combine text and images (hate, extremism, self-harm, erotic harms), from the image input evaluations first introduced with ChatGPT Agent.

Not checked against a maintainer's page.

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.