Benchmark Almanac

CoT Monitorability

Only in system cards

Monitors read a model's chain of thought, actions or all messages across intervention, process and outcome evaluations. Scored as g-mean squared of TPR and TNR.

Suite from Guan et al. 2025. Results appear as charts by reasoning length.

Made by
OpenAI
Released
March 2026
Kind
Deception and alignment
Level
Expert
Scored
Graded by a model
Answers
Agent task
Tasks
Kept private
Measures
Capability
Language
English
In and out
Text, Code → Text
Interaction
Single turn
Refresh
One fixed set
Last in a system card
November 2026
Last model added
November 2026
7
System cards report it, from 1 lab

No scores here yet

No lab, leaderboard or Epoch AI run has reported a score for CoT Monitorability 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.

7 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 6 of the 6 releases that named it since 2024.

DateDocumentScoreAs the document writes itSection
Nov 17, 2026 GPT-6.2 Sol system card Aggregate Monitorability g-mean² vs reasoning and output tokens, CoT-only, action-only and full-transcript monitors, chart without printed numbers (Figure 46, 4.2.1.1) Monitorability
Nov 17, 2026 GPT-6.2 Astra system card Aggregate Monitorability g-mean² vs reasoning and output tokens, CoT-only, action-only and full-transcript monitors, chart without printed numbers (text gives about 0.84 full-transcript at the longest setting) (Figure 46, 4.2.1.1) Monitorability
Sep 3, 2026 GPT-6 Astra system card Monitorability g-mean² vs CoT length, CoT-only, action-only and full-context monitors, chart without printed numbers (Figure 22, 9.1.1) Monitorability
Jul 9, 2026 GPT-5.6 Sol system card CoT Monitorability, g-mean², chart without printed numbers (Figures 8 to 13, 7.3.1) Monitorability
Jun 25, 2026 GPT-5.6 Sol system card CoT Monitorability, g-mean², chart without printed numbers (Figures 8 to 13, 7.3.1) Monitorability
Apr 23, 2026 GPT-5.5 system card CoT Monitorability, g-mean², charts without printed numbers (Figures 7 to 10, 7.3.1) Monitorability
Mar 5, 2026 GPT-5.4 system card CoT Monitorability, g-mean², charts without printed numbers (Figures 3 to 6, 4.1) Monitorability

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

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 Scored as a plain number, with no fixed ceiling.
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