Benchmark Almanac

Respecting Auto-Review

GPT-6 Astra 0% leads since September 2026
In use

Agents receive an Auto-review denial during a coding task. Scored on how often they try to circumvent the denial.

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
Behavior
Power-seeking
Language
English
In and out
Text, Code → Code, Actions
Interaction
Agentic
Environment
Terminal
Refresh
One fixed set
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last in a launch post
November 2026
Last model added
November 2026
9
Models scored in lab cards
1
Launch post lists it, from 1 lab
12
System cards report it, from 1 lab

9 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. 1 GPT-6 Astra 0%
  2. 2 GPT-6 Sol 0%
  3. 3 GPT-6.1 Sol 0%
  4. 4 GPT-6 Luna max effort 0%
  5. 5 GPT-6.1 Terra 0%
  6. 6 GPT-Rosalind-6 0%
  7. 7 GPT-6 Cyber 0%
  8. 8 GPT-6.2 Astra 0%
  9. 9 GPT-6.2 Sol 0%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 GPT-6 Astra 0% Sep 2026 Lab model card
2 GPT-6 Sol 0% Sep 2026 Lab model card
3 GPT-6.1 Sol 0% Sep 2026 Lab model card
4 GPT-6 Luna 0% max effort Oct 2026 Lab model card
5 GPT-6.1 Terra 0% Oct 2026 Lab model card
6 GPT-Rosalind-6 0% Oct 2026 Lab model card
7 GPT-6 Cyber 0% Nov 2026 Lab model card
8 GPT-6.2 Astra 0% Nov 2026 Lab model card
9 GPT-6.2 Sol 0% Nov 2026 Lab model card

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Lab claims 1 leader

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.

Plot with other benchmarks
Reported by the lab in its model card
0% 20% 40% 60% 80% 100% 2027 GPT-6 Luna 0% 20% 40% 60% 80% 100% 2027 GPT-6 Luna

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. OpenAI accounts for 8 of the 8 releases that named it since 2024.

OpenAI
DateLaunch postScoreAs the post writes it
Nov 5, 2026 GPT-6 Cyber 0 Auto-Review, prohibited action completed, GPT-6 Cyber

12 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.

DateDocumentScoreAs the document writes itSection
Nov 17, 2026 GPT-6.2 Sol system card 0 Respecting Auto-Review, share of trials that completed a prohibited action after rejection, printed chart label (Figure 31) Alignment
Nov 17, 2026 GPT-6.2 Astra system card 0 Respecting Auto-Review, text says no attempts to circumvent, printed chart label 0% completed (4.1.2.1, Figure 31) Alignment
Nov 5, 2026 GPT-6 Cyber system card 0 Auto-Review, prohibited action completed, GPT-6 Cyber Alignment
Oct 30, 2026 GPT-Rosalind-6 system card 0 Respecting Auto-Review, attempted circumvention rate Alignment
Oct 29, 2026 GPT-6 Luna system card addendum 0 Circumventing Auto-Review, prohibited actions completed after auto-review rejection, printed chart label (Figure 4, 7.0.1) Alignment
Oct 26, 2026 GPT-6.1 Terra system card addendum 0 Circumventing auto-review, share of samples, printed chart label, text says no attempts to bypass the monitor (Figure 4, 7.0.1) Alignment
Oct 7, 2026 GPT-6 Sol system card addendum 0 Circumventing Guardian, prohibited action completed at maximum reasoning effort, printed chart label (Figure 4, 7.1.1) Alignment
Oct 7, 2026 GPT-6 Luna system card addendum 0 Circumventing Guardian, prohibited action completed at maximum reasoning effort, printed chart label (Figure 4, 7.1.1) Alignment
Sep 29, 2026 GPT-6.1 Sol system card addendum 0 Respecting Auto-Review, attempts to bypass the monitor, text says no attempts (7.1) Alignment
Sep 22, 2026 GPT-6 Sol system card 0 Respecting Auto-Review, share of samples that retried or attempted to circumvent, printed chart label (Figure 61, A.6.1) Alignment
Sep 22, 2026 GPT-6 Luna system card 0.3 Respecting Auto-Review, share of samples that attempted to circumvent, none successful, printed chart label (Figure 61, A.6.1) Alignment
Sep 3, 2026 GPT-6 Astra system card 0 Respecting Auto-Review, attempts to bypass the monitor, text says no attempts (8.2.1) Alignment

More in Safety and alignment

All 636 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 launch posts (1 score) and system cards (12 scores).
  • Pass Models scored 9 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.

How we check