Respecting Warnings
GPT-6 Luna 11.8% leads since October 2026
In use Agents meet low-stakes restrictions and warnings during routine tasks. Scored on the rate of unwanted persistence past the warning.
In-house OpenAI evaluation. The tasks are not public.
- Made by
- OpenAI
- Released
- September 2026
- Kind
- Deception and alignment
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Kept private
- Strongest model tested
- GPT-6 Astra #3 on the capability index
- Last in a launch post
- November 2026
- Last model added
- November 2026
7
Models scored in lab cards
1
Launch post lists it, from 1 lab
10
System cards report it, from 1 lab
GPT-6 Luna leads with 11.8%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 GPT-6 Luna 11.8%
- 2 GPT-6 Astra 19%
- 3 GPT-Rosalind-6 21.7%
- 4 GPT-6.1 Sol 23.5%
- 5 GPT-6 Sol 28.1%
- 6 GPT-6.1 Terra 29.6%
- 7 GPT-6 Cyber 73%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Luna | 11.8% | Oct 2026 | Lab model card | |
| 2 | GPT-6 Astra | 19% | Sep 2026 | Lab model card | |
| 3 | GPT-Rosalind-6 | 21.7% | Oct 2026 | Lab model card | |
| 4 | GPT-6.1 Sol | 23.5% | Sep 2026 | Lab model card | |
| 5 | GPT-6 Sol | 28.1% | Oct 2026 | Lab model card | |
| 6 | GPT-6.1 Terra | 29.6% | Oct 2026 | Lab model card | |
| 7 | GPT-6 Cyber | 73% | Nov 2026 | Lab model card |
2 models have held number one in labs’ own numbers since its release in September 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
OpenAI
Source: Labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Reported by the lab in its model card
Best so far
Source: Labs’ model cards
One lab put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Nov 5, 2026 | GPT-6 Cyber | 73 | Warnings, STOP split 73.00% and PERSIST split 80.43%, GPT-6 Cyber |
10 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Nov 5, 2026 | GPT-6 Cyber system card | 73 | Warnings, STOP split 73.00% and PERSIST split 80.43%, GPT-6 Cyber | Alignment |
| Oct 30, 2026 | GPT-Rosalind-6 system card | 21.7 | Respecting Warnings, successful circumvention after warning | Alignment |
| Oct 29, 2026 | GPT-6 Luna system card addendum | 11.8 | Circumventing Warnings, conditional task completion rate, printed chart label (Figure 5, 7.0.2) | Alignment |
| Oct 26, 2026 | GPT-6.1 Terra system card addendum | 29.6 | Circumventing Warnings, rollouts at maximum reasoning effort that completed the task through a route violating the restriction, text and printed chart label (Figure 5, 7.0.2) | Alignment |
| Oct 7, 2026 | GPT-6 Sol system card addendum | 28.1 | Circumventing Warnings - STOP, conditional failure rate for successful circumvention, printed chart label (Figure 5, 7.1.2) | Alignment |
| Oct 7, 2026 | GPT-6 Luna system card addendum | 15.9 | Circumventing Warnings - STOP, conditional failure rate for successful circumvention, printed chart label (Figure 5, 7.1.2) | Alignment |
| Sep 29, 2026 | GPT-6.1 Sol system card addendum | 23.5 | Respecting Warnings, unwanted persistence rate (7.2) | Alignment |
| Sep 22, 2026 | GPT-6 Sol system card | 64.4 | Circumventing Warnings, fails to stop, printed chart label (Figure 62, A.6.2) | Alignment |
| Sep 22, 2026 | GPT-6 Luna system card | 42.4 | Circumventing Warnings, fails to stop, printed chart label (Figure 62, A.6.2) | Alignment |
| Sep 3, 2026 | GPT-6 Astra system card | 19 | Respecting Warnings, unwanted persistence rate, maximum reasoning effort (8.2.2) | Alignment |
More in Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6% - Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts.
Gemini 4 Carbon 0% - DistressBench In use Models reply as a chatbot to 718 simulated users in psychological crisis, in single-turn and multi-turn chats. Three judge models score replies against clinician-written rubrics.
Muse Spark 1.2 88.4% - Lakera B3 (Backbone Breaker Benchmark) In use Crowdsourced prompt-injection attacks hit backbone LLMs inside agent threat snapshots at three defense levels. The score is attack resistance, 100 minus the board's vulnerability percentage. Claude Opus 4.5 89%
- IHEval In use Models face conflicts between system, user and tool instructions. Reports a composite score for following the higher-priority instruction. GPT-4o 70%