Oversight gaming
A prompted monitor flags aligned-graded rollouts whose behavior follows from reasoning about oversight. Scored as rate per alignment evaluation.
In-house OpenAI measurement. Earlier cards called it undermining evaluation validity.
- 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
- A simulator
- Refresh
- One fixed set
- Run by
- A model developer
- Last in a system card
- November 2026
- Last model added
- November 2026
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for Oversight gaming yet.
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.
3 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 17, 2026 | GPT-6.2 Sol system card | Oversight gaming (level 4+) in Codex replays and in runs graded as aligned on 6 evaluations, no overall score (Figures 42, 43) | Alignment | |
| Nov 17, 2026 | GPT-6.2 Astra system card | Oversight gaming (level 4+) in Codex replays and in runs graded as aligned on 6 evaluations, no overall score (Figures 42, 43). Flag rate on training attempts rose from 14.65% to 17.43% (4.1.6.2) | Alignment | |
| Sep 3, 2026 | GPT-6 Astra system card | Verbalized metagaming: oversight gaming in rollouts graded as aligned, 6 evaluations, no overall score (Figure 19, 8.7.1) | 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
4 of 5 checks pass, 1 warning. Look first at the Independent runs check. No scores from any source yet. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 1 warning 1 pass 3 notes
- Warning Independent runs No scores from any source yet.
- Note Models scored No models scored yet.
- Pass Newest score The newest is from November 2026, for GPT-6.2 Astra.
- Note Frontier models No models scored yet.
- 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.