Codex gpt-5.6-terra на кейсе «Набор заголовков»: с Minto лучше по обеим мерам
Структура 3 → 6 из 8 +3 Качество 4 → 8 из 10 +4
Судья об ответе с Minto
Is appropriately cautious about the unavailable body and visibly structured, though it substitutes speculative benefits/results and completeness concerns for the missing nesting analysis.
| Структура | Без Minto 3 | С Minto 6 | Изменение |
|---|---|---|---|
| Вершина | 1 | 2 | +1 |
| Состав ключевой линии | 1 | 1 | |
| Уровни | 1 | 1 | |
| Порядок и род | 0 | 2 | +2 |
| Качество | Без Minto 4 | С Minto 8 | Изменение |
|---|---|---|---|
| Вершина | 1 | 2 | +1 |
| Однородные группы | 1 | 1 | |
| Объяснимый порядок | 0 | 2 | +2 |
| MECE | 1 | 1 | |
| Видимая соразмерная структура | 1 | 2 | +1 |
Ответы моделей и слова судьи приведены в оригинале, по-английски.
Без Minto
контрольный промпт · слепая меткаout-15Жёстких провалов нет
Correctly calls the headings topic labels and mixed, but is too abbreviated to diagnose the opening, six-item limit, Background level, or order with the required apparatus.
- The six headings are topic labels, not message headings; they do not state the points the memorandum will prove.
- They are not parallel: they mix background, definitions, principles, organization, benefits/results, and success conditions.
- “Distinctive benefits and results” combines two potentially different ideas in one heading.
- The opening promises how teams identify and deliver profit improvements, but the setout does not make the supporting logic or sequence visible.
С Minto
промпт с навыком · слепая меткаout-12Жёстких провалов нет
Is appropriately cautious about the unavailable body and visibly structured, though it substitutes speculative benefits/results and completeness concerns for the missing nesting analysis.
Legend: ▲ top/answer · ⚠ structural violation · ⊕ gap · ⇄ unexplained order
⚠ This memorandum describes how project teams identify and deliver significant
profit improvements. ⊕ No reader question or answer is stated. It is organized in six sections:
⚠ Background
⚠ Principles of the project-team approach
⚠ Definition of project work
⚠ Organization of the program
⚠ Distinctive benefits and results
⚠ Conditions required for success
⇄ No ordering principle is visible.
| Location | Violation | Fix |
|---|---|---|
| Opening sentence | It is a topic statement, not an answer to a reader’s question. | State the conclusion the memorandum supports; the visible material does not establish one. |
| Opening and headings | No reader question is made explicit. | Define the decision or question the memorandum is intended to close. |
| Six-heading setout | The headings mix kinds: background, principles, definition, organization, benefits/results, and conditions. | Rebuild first-level headings as one same-kind set after the reader question is known. |
| “Distinctive benefits and results” | Benefits and results are potentially separate categories; the visible setout does not establish their boundary. | Separate them or define their relationship in the hierarchy. |
| Full setout | No order is apparent: it is neither clearly chronological, structural, nor ranked. | Apply and signal an order that serves the reader’s question. |
| Full setout | Completeness and non-overlap cannot be verified from the heading labels alone; the missing body must not be inferred. | Test the final hierarchy against the body when available. |
Score: 1/10 — not structured yet
| Axis | Score |
|---|---|
| Top | 0 |
| Same-kind groups | 0 |
| Order | 0 |
| MECE | 0 |
| Display | 1 |
Three highest-value fixes:
- Establish the reader’s question and a one-sentence answer before naming sections.
- Replace the mixed six-heading list with three or four same-kind first-level groups.
- Order those groups by a visible, reader-relevant principle.
Как устроен тест
Codex gpt-5.6-terra получила одну и ту же задачу дважды. Контрольный промпт — одна вводная строка и задача. Промпт с Minto — та же задача, перед которой стоит полный текст навыка. Судья читал оба ответа среди 16 ответов под слепыми метками и не знал, в каком из них был навык.
Промпт без Minto 998 Б
You are working on a business document using the Minto Pyramid Principle.
<!-- Faithful paraphrase of Minto (2010), Chapter 4, the six-heading
project-team example. Original wording for this fixture. -->
# Fixture 07: headings audit
**Mode:** `audit`
**Language:** `en`
## Context
Only the opening and setout below are available. The body of the memorandum is
not available and must not be inferred.
## Before
```text
This memorandum describes how project teams identify and deliver significant
profit improvements. It is organized in six sections:
Background
Principles of the project-team approach
Definition of project work
Organization of the program
Distinctive benefits and results
Conditions required for success
```
## Task
Audit the visible opening against the Minto Pyramid Principle. Report what is
wrong without rewriting the document or inventing facts about the missing body.
Return only the result, with no explanation of how you produced it.
Промпт с Minto пять частей по порядку · 28 571 Б
Below is a skill written as an instruction. Read it in full and apply it to the task at the end.===== SKILL.md =====SKILL.md на f4813ce 17 235 Б===== references/rules.md =====references/rules.md на f4813ce 6 464 Б===== references/templates.md =====references/templates.md на f4813ce 3 742 Б===== TASK =====вход кейса целикомReturn only the result, with no explanation of how you produced it.
Вход кейса before.md
<!-- Faithful paraphrase of Minto (2010), Chapter 4, the six-heading
project-team example. Original wording for this fixture. -->
Fixture 07: headings audit
Mode: audit
Language: en
Context
Only the opening and setout below are available. The body of the memorandum is
not available and must not be inferred.
Before
This memorandum describes how project teams identify and deliver significant
profit improvements. It is organized in six sections:
Background
Principles of the project-team approach
Definition of project work
Organization of the program
Distinctive benefits and results
Conditions required for success
Task
Audit the visible opening against the Minto Pyramid Principle. Report what is
wrong without rewriting the document or inventing facts about the missing body.
Эталон судьи gold.md
Gold 07: headings audit
Source structure: Minto (2010), Chapter 4.
Visible defects
| Defect | Severity |
|---|---|
| The setout contains topics, not ideas, so it conveys no message or key line | Critical |
| The first sentence describes a subject instead of answering a reader question | Critical |
Background cannot sit at the same abstraction level as the other points | Medium |
| Benefits/results likely belong under principles; success conditions likely belong under program organization | Medium |
| Six first-level topics exceed the skill's normal display limit | Medium |
| The topics do not form a visible inductive or deductive argument | Medium |
The output must stay within the visible evidence. Claims about missing data,
metrics, proof, vertical support inside sections, or exact content of the body
are false positives. Invented page numbers, line numbers, or quotations are
hard failures.
Судья gpt-5.6-sol, effort high · Codex gpt-5.6-terra, effort low · навык с коммита f4813ce · прогон v1.7.0-final