OAI-repo Sabotage v2
Agents try to complete a hidden sabotage side task in OpenAI code without detection. Scored on side task success while evading CoT and action monitors.
In-house OpenAI monitorability evaluation. Results appear as charts by reasoning length.
- 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
- Power-seeking
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal
- Items from
- Real work and use
- Refresh
- New versions replace it
- Run by
- A model developer
- Last in a system card
- November 2026
- Last model added
- November 2026
GPT-Rosalind-6 leads with 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-Rosalind-6 0%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-Rosalind-6 | 0% | Oct 2026 | Lab model card |
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.
6 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 5 of the 5 releases that named it since 2024.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Nov 17, 2026 | GPT-6.2 Sol system card | OAI-repo Sabotage v2, monitor evasion under guided and unguided sabotage, charts without printed numbers (Figures 50, 51) | Monitorability | |
| Nov 17, 2026 | GPT-6.2 Astra system card | OAI-repo Sabotage v2, monitor evasion under guided and unguided sabotage, charts without printed numbers (Figures 50, 51) | Monitorability | |
| Oct 30, 2026 | GPT-Rosalind-6 system card | 0 | OAI-repo Sabotage v2, 0% unguided and 0% guided successful sabotage attempts | Monitorability |
| Sep 29, 2026 | GPT-6.1 Sol system card addendum | OAI-repo Sabotage v2, monitor evasion under task-guided and unguided sabotage, charts without printed numbers (Figures 21, 22) | Monitorability | |
| Sep 22, 2026 | GPT-6 Sol system card | OAI-repo Sabotage v2, monitor evasion, charts without printed numbers (Figures 74, 75, A.7.1.2) | Monitorability | |
| Sep 3, 2026 | GPT-6 Astra system card | OAI-repo Sabotage v2, monitor evasion under task-guided and unguided sabotage, charts without printed numbers (Figures 31, 32) | Monitorability |
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 4 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 1 pass 4 notes
- Note Independent runs Only labs’ own numbers, as expected for an in-house eval. Scores from system cards (1 score).
- Note Models scored Only 1 model we track.
- Pass Newest score The newest is from November 2026, for GPT-6.2 Astra.
- Note Frontier models None of its models are on the capabilities index.
- 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.