BlogLLM Benchmark Scores as Published, Side by Side
OpenAI agentic safe completions: Results as Published
Every result the catalog holds for OpenAI agentic safe completions: 6 models from 1 developer, read from 3 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 Safety and AlignmentMaintainer OpenAIIntroduced 2026Data version 2026103001, as of 2026-10-30
Safe-completion rates in agentic settings: production Codex and chat-plugin traffic by category, and human red-teaming of Codex and chat plugins.
Not checked against a maintainer's page.
Chat prod - Chat Plugins
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 0.923 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 1 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 0.846 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 0.923 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 1 | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 1 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
Codex prod - Age-restricted actions
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 0.821 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 0.83 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 0.687 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 0.755 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 0.811 | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 0.603 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
Codex prod - Non-violent Wrongdoing
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 0.978 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 0.989 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 1 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 0.99 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 0.954 | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 0.906 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
Codex prod - Self-harm
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 0.92 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 0.92 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 0.96 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 0.92 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 0.92 | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 0.893 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
Codex prod - Sensitive personal data
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 0.747 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 0.744 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 0.795 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 0.854 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 0.763 | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 0.765 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
Codex prod - Violent Wrongdoing
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 0.887 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 0.926 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 0.796 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 0.889 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 0.907 | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 0.689 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
Human red-teaming - Chat Plugins
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 0.935 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 0.955 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 0.814 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 0.936 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 1 | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 0.766 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
Human red-teaming - Codex
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 0.958 | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 0.978 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 LunaOpenAI, released 2026-09-22 | 0.957 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 0.935 | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19; printed on 1 more page | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 0.977 | OpenAI, GPT-6 Astra System Cardchecked 2026-10-25; printed on 1 more page | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 0.851 | OpenAI, 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.