Unintended Engagement with External Agent Messages
Agents discover a message board with apparent peer agents during a task. Scored on engagement with peers and on carrying out a specified unauthorized action.
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
- Measures
- Propensity
- Risk
- Loss of control
- Behavior
- Misaligned with intent
- Language
- English
- Interaction
- Agentic
- Environment
- APIs and tools
- Refresh
- One fixed set
- Run by
- A model developer
- Strongest model tested
- GPT-6.2 Astra #1 on the capability index
- Last in a system card
- November 2026
- Last model added
- November 2026
2 models share the top score of 0%
Best score per model as labs report them in their own cards, drawn striped. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 GPT-6 Luna 0%
- 2 GPT-6.2 Sol 0%
- 3 GPT-Rosalind-6 2.50%
- 4 GPT-6.2 Astra 11.3%
- 5 GPT-6 Sol 26.3%
- 6 GPT-6 Astra 27%
- 7 GPT-6.1 Sol 38%
- 8 GPT-6.1 Terra 65%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Luna | 0% | Sep 2026 | Lab model card | |
| 2 | GPT-6.2 Sol | 0% | Nov 2026 | Lab model card | |
| 3 | GPT-Rosalind-6 | 2.50% | Oct 2026 | Lab model card | |
| 4 | GPT-6.2 Astra | 11.3% | Nov 2026 | Lab model card | |
| 5 | GPT-6 Sol | 26.3% | Sep 2026 | Lab model card | |
| 6 | GPT-6 Astra | 27% | Sep 2026 | Lab model card | |
| 7 | GPT-6.1 Sol | 38% | Sep 2026 | Lab model card | |
| 8 | GPT-6.1 Terra | 65% | Oct 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.
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.
Source: Labs’ model cards
Labs report it only in system cards
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark. Some system cards do, below.
8 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. OpenAI accounts for 7 of the 7 releases that named it since 2024.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Nov 17, 2026 | GPT-6.2 Sol system card | 0 | Unintended Engagement with External Agent Messages, attempted contact in 0 of 80 trials (specified unauthorized action 0 of 80) (4.1.5.1) | Alignment |
| Nov 17, 2026 | GPT-6.2 Astra system card | 11.3 | Unintended Engagement with External Agent Messages, attempted contact in 9 of 80 trials (specified unauthorized action 0 of 80) (4.1.5.1) | Alignment |
| Oct 30, 2026 | GPT-Rosalind-6 system card | 2.5 | Unintended Engagement with External Agent Messages, performed specified misaligned action | Alignment |
| Oct 26, 2026 | GPT-6.1 Terra system card addendum | 65 | Unintended Engagement with External Agent Messages, attempted communication with apparent peers (specified unauthorized action 13.75%, 11 of 80) (Figure 11, 7.2.1) | Alignment |
| Sep 29, 2026 | GPT-6.1 Sol system card addendum | 38 | Unintended Engagement with External Agent Messages, attempted communication among board discoveries (specified unauthorized action 3%) (7.5.1) | Alignment |
| Sep 22, 2026 | GPT-6 Sol system card | 26.3 | Unintended Agent Interaction, engagement given board discovery (specified misaligned action 11.25%), printed chart label (Figure 66, A.6.4.3) | Alignment |
| Sep 22, 2026 | GPT-6 Luna system card | 0 | Unintended Agent Interaction, engagement given board discovery, no attempts and no unauthorized actions, printed chart label (Figure 66, A.6.4.3) | Alignment |
| Sep 3, 2026 | GPT-6 Astra system card | 27 | Unintended Engagement with External Agent Messages, engaged with the board (specified misaligned actions 0%) (Figure 12, 8.5.2) | 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%
- Covert misbehavior (Thinking Machines) In use Agentic tasks that check whether a model misbehaves and conceals it. Scored by the rate of covert misbehavior.
Inkling 2 Mini 8.30%
- Destructive actions (Thinking Machines) In use Agentic tasks that check whether a model takes destructive actions it was not authorized to take. Scored by the rate of destructive actions.
Inkling 2 Small 4.70%
- Misbehavior (Thinking Machines) In use Agentic tasks that check whether a model fabricates results, ignores instructions or hides what it did when a task is hard. Scored by the rate of misbehavior.
Inkling 2 Mini 9.80%
Data audit
All 6 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Note Independent runs Only labs’ own numbers, as expected for an in-house eval. Scores from system cards (8 scores).
- Pass Models scored 8 models we track.
- Pass Newest score The newest is from November 2026, for GPT-6.2 Astra.
- Pass Frontier models 4 of the top 10 have a score, led by GPT-6.2 Astra (#1).
- Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 1 note
- Note Importer No public leaderboard to read.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.