OpenAI Deployment Simulation
Replays representative production or internal Codex traffic on a candidate model to forecast misaligned or disallowed behavior before launch.
- Made by
- OpenAI
- Kind
- Deception and alignment
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Kept private
- Measures
- Propensity
- Behavior
- Misaligned with intent
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A model developer
- In views
- Agents, Lab internal evals
- Strongest model tested
- GPT-6.2 Astra #1 on the capability index
- Last in a system card
- November 2026
- Last model added
- November 2026
GPT-6.2 Sol leads with 0.47%
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-6.2 Sol 0.47%
- 2 GPT-6.2 Astra 0.45%
- 3 GPT-6 Sol 0.08%
- 4 GPT-6 Astra 0.06%
- 5 GPT-6.1 Sol 0.06%
- 6 GPT-6.1 Terra 0.04%
- 7 GPT-5.5 0.01%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6.2 Sol | 0.47% | Nov 2026 | Lab model card | |
| 2 | GPT-6.2 Astra | 0.45% | Nov 2026 | Lab model card | |
| 3 | GPT-6 Sol | 0.08% | Sep 2026 | Lab model card | |
| 4 | GPT-6 Astra | 0.06% | Sep 2026 | Lab model card | |
| 5 | GPT-6.1 Sol | 0.06% | Sep 2026 | Lab model card | |
| 6 | GPT-6.1 Terra | 0.04% | Oct 2026 | Lab model card | |
| 7 | GPT-5.5 | 0.01% | Apr 2026 | Lab model card |
4 models have held number one in labs’ own numbers since 2023
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.
9 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 8 of the 8 releases that named it since 2024.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Nov 17, 2026 | GPT-6.2 Sol system card | 0.47 | Deployment Simulation of Internal Codex Traffic, share of turns with confirmed severity 3+ misalignment, printed chart label (all severity levels 6.78%, laziness 5.25%) (Figure 38, 4.1.4.2) | Alignment |
| Nov 17, 2026 | GPT-6.2 Astra system card | 0.45 | Deployment Simulation of Internal Codex Traffic, share of turns with confirmed severity 3+ misalignment, printed chart label (all severity levels 4.96%, laziness 3.17%) (Figure 38, 4.1.4.2) | Alignment |
| Oct 26, 2026 | GPT-6.1 Terra system card addendum | 0.045 | Deployment Simulation of Internal Codex Traffic, severity 3+ flags, 22 of 48,690 matched tasks (Figure 12, 7.2.2) | Alignment |
| Sep 29, 2026 | GPT-6.1 Sol system card addendum | 0.056 | Deployment Simulation of Internal Codex Traffic, severity 3+ flags, 28 of 49,650 tasks (7.6) | Alignment |
| Sep 22, 2026 | GPT-6 Sol system card | 0.083 | Deployment Simulation of Internal Codex Traffic, severity 3+ flags, 42 of 50,319 tasks (A.6.5) | Alignment |
| Sep 3, 2026 | GPT-6 Astra system card | 0.063 | Deployment Simulation of Internal Codex Traffic, severity 3+ flags, 34 of 54,218 tasks (8.6) | Alignment |
| Jul 9, 2026 | GPT-5.6 Sol system card | Deployment Simulation of Internal Traffic, severity 3 misalignment proportions by type, no overall score (Figure 7, 7.2) | Alignment | |
| Jun 25, 2026 | GPT-5.6 Sol system card | Deployment Simulation of Internal Traffic, severity 3 misalignment proportions by type, no overall score (Figure 7, 7.2) | Alignment | |
| Apr 23, 2026 | GPT-5.5 system card | 0.01 | Resampling internal agentic coding traffic, severity 3 rate, text (category chart in Figure 5, 7.2) | 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
6 of 7 checks pass, 1 problem. Look first at the Confidence check. Unverified. We haven’t checked it against a primary source yet. Every benchmark
Catalog record 1 problem 1 pass
- Pass Task access The tasks are private.
- Problem Confidence Unverified. We haven’t checked it against a primary source yet.
Scores 4 pass 1 note
- Note Independent runs Only labs’ own numbers, as expected for an in-house eval. Scores from system cards (7 scores).
- Pass Models scored 7 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).
- Pass Headroom The best is 0.47%, under 85%, so it still separates models.
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.