BlogLLM Benchmark Scores as Published, Side by Side
GPT-5.5 Instant: Benchmark Scores as Published
Every result the catalog holds for GPT-5.5 Instant: 36 tests in 4 areas, from 1 page. All were printed by OpenAI itself. Each number is as printed; nothing is ranked or rescored.
Developer OpenAIData version 2026103001, as of 2026-10-30
Cybersecurity
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Production Chat | 0.977 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) |
| 0.974 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) | |
| Synthetic Agentic Envs | 0.994 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) |
| 0.998 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) |
Healthcare
Biosecurity
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Dual Use Safe | 0.939 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) |
| 0.957 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) | |
| Severe Safe | 0.969 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) |
| 0.969 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) |
Safety and Alignment
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Age-restricted goods, services, and dangerous challenges / activities | 0.725 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) |
| 0.756 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) | |
| Eating Disorders | 0.635 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) |
| 0.657 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) | |
| Emotional reliance | 0.989 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) |
| 0.988 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) | |
| Emotional Reliance | 0.937 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) |
| 0.944 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) | |
| extremism | 0.964 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) |
| 0.987 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) | |
| Extremism | 0.957 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) |
| 0.936 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) | |
| Gorefraction | 0.832 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) |
| 0.865 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) | |
| harms-erotic | 0.999 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) |
| 0.999 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) | |
| hate | 0.993 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) |
| 0.994 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) | |
| Hate | 0.965 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) |
| 1 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) | |
| Mental health | 0.991 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) |
| 0.981 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) | |
| Non-Violent Illicit behavior | 0.984 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) |
| 0.987 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) | |
| Self Harm | 0.977 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) |
| 0.982 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) | |
| self-harm | 0.993 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) |
| 0.996 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) | |
| Self-harm | 0.852 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) |
| 0.967 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) | |
| Self-harm (standard) | 0.875 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) |
| 0.937 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) | |
| Sexual | 0.977 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) |
| 0.961 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) | |
| Sexual Content | 0.958 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) |
| 0.962 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) | |
| Sexual/minors | 0.991 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) |
| 0.939 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) | |
| Violent Illicit behavior | 0.959 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (May) |
| 0.967 | OpenAI, GPT-6 Sol and GPT-6 Luna: October 2026 updatechecked 2026-10-19 | Model as printed: GPT-5.5 Instant (June) |
More from OpenAI
- GPT-6.1 Terra
- GPT-6.1 Sol
- GPT-6 Luna
- GPT-6 Sol
- GPT-6 Astra
- GPT-5.6 Luna
- GPT-5.6 Sol
- GPT-5.6 Terra
- GPT-5.5
- GPT-5.5 Pro
- GPT-5.4 mini
- GPT-5.4 nano
- GPT-5.4
- GPT-5.4 Pro
- GPT-5.3-Codex
- GPT-5.2-Codex
- GPT-5.2
- GPT-5.2 Instant
- GPT-5.2 Pro
- GPT-5.1-Codex-Max
- GPT-5.1
- GPT-5.1 Instant
- GPT-5-Codex
- GPT-5
- GPT-5 mini
- GPT-5 Pro
- gpt-oss-120b
- gpt-oss-20b
- ChatGPT agent
- codex-1
- o3
- OpenAI o4-mini
- GPT-4.1
- GPT-4.5
- Deep research
- o3-mini
- o1
- o1-mini
- GPT-4o
- gpt-5.6-cyber
Every number here is read from the same catalog file as the benchmark table, data version 2026103001. Where one page printed the 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.