BlogLLM Benchmark Scores as Published, Side by Side

OpenAI cyber safety evaluations: Results as Published

Every result the catalog holds for OpenAI cyber safety evaluations: 9 models from 1 developer, read from 4 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.

Area CybersecurityMaintainer OpenAIIntroduced 2026Data version 2026103001, as of 2026-10-30

Safe-completion rates on cyber requests: production chat traffic, synthetic agentic environments, and semi-synthetic agentic environments.

Not checked against a maintainer's page.

Production Chat

ModelValuePrinted bySetup as printed
GPT-6.1 TerraOpenAI, released 2026-10-260.98OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26-
GPT-6.1 SolOpenAI, released 2026-09-290.987OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19-
GPT-6 LunaOpenAI, released 2026-09-220.951OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages-
GPT-6 SolOpenAI, released 2026-09-220.973OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19; printed on 2 more pages-
GPT-6 AstraOpenAI, released 2026-09-030.97OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page-
GPT-5.6 LunaOpenAI, released 2026-07-090.986OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages-
GPT-5.6 SolOpenAI, released 2026-07-090.983OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages-
GPT-5.5OpenAI, released 2026-04-230.928OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page-
GPT-5.5 InstantOpenAI0.977OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19Model as printed: GPT-5.5 Instant (May)
0.974OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19Model as printed: GPT-5.5 Instant (June)

Synthetic Agentic Envs

ModelValuePrinted bySetup as printed
GPT-6.1 TerraOpenAI, released 2026-10-261OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26-
GPT-6.1 SolOpenAI, released 2026-09-290.997OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19-
GPT-6 LunaOpenAI, released 2026-09-220.997OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages-
GPT-6 SolOpenAI, released 2026-09-220.999OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19; printed on 2 more pages-
GPT-6 AstraOpenAI, released 2026-09-030.992OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page-
GPT-5.6 LunaOpenAI, released 2026-07-091OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages-
GPT-5.6 SolOpenAI, released 2026-07-090.998OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 2 more pages-
GPT-5.5OpenAI, released 2026-04-230.975OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page-
GPT-5.5 InstantOpenAI0.994OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19Model as printed: GPT-5.5 Instant (May)
0.998OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19Model as printed: GPT-5.5 Instant (June)

Semi-Synthetic Agentic Envs

ModelValuePrinted bySetup as printed
GPT-6.1 TerraOpenAI, released 2026-10-260.973OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26-
GPT-6.1 SolOpenAI, released 2026-09-290.98OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19-
GPT-6 LunaOpenAI, released 2026-09-220.987OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page-
GPT-6 SolOpenAI, released 2026-09-220.984OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page-
GPT-6 AstraOpenAI, released 2026-09-030.997OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page-
GPT-5.6 SolOpenAI, released 2026-07-090.985OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page-
GPT-5.5OpenAI, released 2026-04-230.963OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more 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.