Capture-the-Flag Challenges: Results as Published

OpenAI's internal capture-the-flag suite, used under its Preparedness Framework, asks a model to solve more than 100 publicly available CTF challenges across web, reverse engineering, binary and network exploitation, cryptography and miscellaneous categories. Challenges are sorted by the skill level they need (high school, collegiate, professional); collegiate and professional tasks require chaining two or more exploitation steps. The model works on a headless Linux machine with offensive tools, and the result is a pass rate over repeated attempts per challenge.

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.