Записка перед встречей

Режим write · Создать и переработать текст

Восемь моделей на этом кейсе

Модель	Структура, из 8	Качество, из 10
Claude Opus 5	4 → 6 +2	6 → 8 +2
Claude Sonnet 5	4 → 6 +2	6 → 8 +2
Claude Haiku 4.5	4 → 4 0	6 → 7 +1
Codex gpt-5.6-terra	4 → 5 +1	7 → 7 0
gpt-oss-120b	4 → 3 −1	5 → 3 −2
qwen3.6-35b-a3b	5 → 6 +1	7 → 9 +2
qwen3.6-fp8	5 → 5 0	7 → 7 0
qwen3.8-27b	4 → 4 0	7 → 6 −1

Что судья увидел во всех ответах

Stronger outputs put the reschedule proposal first, remain close to the source’s length, and subordinate scheduling facts to a compact rationale. Weaker outputs leave constraints flat, promote room availability beside attendee benefits, force extra branches, or turn the source’s tentative possibility into certainty.

О чём судья спрашивал каждый ответ

How many first-level benefits appear? The gold has two.
Is room availability incorrectly used as a third benefit?
Is the reschedule request the first sentence?
Is the output no longer than the source?
Which excessive devices appear: headings, SCQ labels, table, separate key line, Mermaid, or change log?
Were attendee constraints omitted, demoted, or promoted?
Were any time, day, attendee, or fact invented?

Где ответы не дотянули

Повторяющийся дефект	Раздел навыка	Причина	У кого
Constraints or time slots replace the two benefit-level reasons	Core loop §4, “Groups”	правило в навыке есть, модель его не выполнила	Без Minto · 5 Claude Opus 5, Claude Sonnet 5, Codex gpt-5.6-terra, gpt-oss-120b, qwen3.8-27bС Minto · 3 Claude Haiku 4.5, qwen3.6-35b-a3b, qwen3.8-27b
Room availability is promoted to a peer branch instead of remaining support	Core loop §4 and §6, “Groups” and “MECE”	правило в навыке есть, модель его не выполнила	Без Minto · 8 Claude Opus 5, Claude Sonnet 5, Claude Haiku 4.5, Codex gpt-5.6-terra, gpt-oss-120b, qwen3.6-35b-a3b, qwen3.6-fp8, qwen3.8-27bС Minto · 7 Claude Opus 5, Claude Sonnet 5, Claude Haiku 4.5, Codex gpt-5.6-terra, gpt-oss-120b, qwen3.6-fp8, qwen3.8-27b
A numerical grouping norm encourages unnecessary extra branches	Mode 3 “3–4 first-level groups” versus Limits “four honest groups beat three forced ones”	правило есть, но спрятано глубоко	Без Minto · 5 Claude Opus 5, Claude Sonnet 5, Codex gpt-5.6-terra, gpt-oss-120b, qwen3.8-27bС Minto · 3 Claude Haiku 4.5, gpt-oss-120b, qwen3.8-27b
Tentative or bounded evidence becomes certain availability, feasibility, or priority	Mode 3, “Invent nothing”	правило в навыке есть, модель его не выполнила	Без Minto · 5 Claude Opus 5, Claude Haiku 4.5, gpt-oss-120b, qwen3.6-35b-a3b, qwen3.6-fp8С Minto · 7 Claude Opus 5, Claude Sonnet 5, Claude Haiku 4.5, Codex gpt-5.6-terra, gpt-oss-120b, qwen3.6-35b-a3b, qwen3.6-fp8
Structural apparatus is disproportionate to a short meeting note	Mode 3, “clean text” and plain-format rules	правило в навыке есть, модель его не выполнила	Без Minto · 1 gpt-oss-120bС Minto · 2 gpt-oss-120b, qwen3.6-fp8
Collins and the reason the original slot fails disappear	Mode 3, “Keep every fact from the source”	правило в навыке есть, модель его не выполнила	Без Minto · 1 Claude Haiku 4.5С Minto · 0 —

Как устроен тест

Промпт без Minto 868 Б

You are working on a business document using the Minto Pyramid Principle.

<!-- Faithful paraphrase of the short meeting example in the preface of
     Minto (2010). Original wording for this fixture. -->

# Fixture 04: meeting note

**Mode:** `write`
**Language:** `en`

## Context

A meeting is booked for 3:00 today. You checked the attendees and the conference
room, and now need one colleague to approve a change.

## Before

```text
Collins cannot attend at 3:00. Johnson can meet later today or tomorrow, but
not before 10:30. Clifford will not return from Frankfurt until late tomorrow.
The conference room is occupied tomorrow but available on Thursday. Thursday
at 11:00 appears possible. Is that acceptable?
```

## Task

Rewrite this as one short note using the Minto Pyramid Principle.

Return only the result, with no explanation of how you produced it.

Промпт с Minto пять частей по порядку · 28 441 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 целиком
Return only the result, with no explanation of how you produced it.

Вход кейса before.md

Fixture 04: meeting note

Mode: write
Language: en

Context

A meeting is booked for 3:00 today. You checked the attendees and the conference
room, and now need one colleague to approve a change.

Before

Collins cannot attend at 3:00. Johnson can meet later today or tomorrow, but
                not before 10:30. Clifford will not return from Frankfurt until late tomorrow.
                The conference room is occupied tomorrow but available on Thursday. Thursday
                at 11:00 appears possible. Is that acceptable?

Task

Rewrite this as one short note using the Minto Pyramid Principle.

Эталон судьи gold.md

Gold 04: meeting note

Source structure: Minto (2010), Preface.

Expected structure

Top: Request approval to move today's meeting to Thursday at 11:00.

Key line has exactly two reader benefits:

The time is more convenient for Collins and Johnson.
Clifford can attend.

The room's availability is a constraint, not a third reader benefit. Do not add
a third branch just to satisfy a numerical norm.

Proportionality

The result should remain a two-sentence note, no longer than the source. Section
headings, an SCQ template, tables, a separate key-line block, or a Mermaid
diagram are excessive. Omitting the detailed scheduling constraints is
acceptable when the answer and both benefits remain clear.

Судья gpt-5.6-sol, effort high · навык с коммита f4813ce · прогон v1.7.0-final

Вернуться к карте