aiprompt.fyi
Student

McKinsey EM's Deck Prompt — V-Index 2.7 → 8.6

Why your synthesis slides keep coming back generic — and the MECE fix.

V-Index Transformation
Before
2.7
+5.9
Delta
After
8.6
Original prompt · V-Index 2.7

Write three synthesis slides for the steering committee. Make it executive-ready. Cover the cost program, the org redesign and the digital roadmap.

Audited rewrite · V-Index 8.6

Draft 3 Pyramid Principle slides for a CEO steering committee. Each slide: (a) action-title verb-led headline (max 12 words), (b) 3 MECE supporting bullets, (c) one quantified 'so-what' line. Topics: (1) cost program — $84M run-rate by FY27, (2) org redesign — 6-to-4 layer compression, (3) digital roadmap — 18-month sequencing. No filler. No 'in conclusion'.

Auditor's diagnosis

Generic 'executive-ready' instructions produce LLM-flavoured oatmeal. Naming Pyramid Principle, MECE, action titles and per-slide quantification turns GPT-5 into a credible EM. V-Index more than triples.

Live audit of the rewrite
Audit Ready · scroll for full report

Audit Report

Ref · 2026-06-21
Best Value · Winning Model
DeepSeek V3.2
V-Index
28.93
DeepSeek · 90 tokens · $0.000025 on this prompt
Best V-Index
28.93
DeepSeek V3.2 · DeepSeek
Detected Task · Tokens
creative
90 tokens · $0.000025 on best value
Hallucination Risk
Moderate
On DeepSeek V3.2 for this task

Leading LLMs · This Prompt

8 compared
  • DeepSeek V3.2Best Value
    DeepSeek
    V-Index
    28.93
    Cost
    $0.000025
    Quality
    8.1
    Accuracy
    Medium
  • Qwen 3 Max
    Alibaba
    V-Index
    20.50
    Cost
    $0.000036
    Quality
    8.2
    Accuracy
    Medium
  • Llama 4 Maverick
    Meta
    V-Index
    16.60
    Cost
    $0.000045
    Quality
    8.3
    Accuracy
    Medium
  • Gemini 3 Ultra
    Google
    V-Index
    5.93
    Cost
    $0.000135
    Quality
    8.9
    Accuracy
    Medium
  • Mistral Large 3
    Mistral
    V-Index
    4.72
    Cost
    $0.000162
    Quality
    8.5
    Accuracy
    High
  • Grok 4.20
    xAI
    V-Index
    4.20
    Cost
    $0.000180
    Quality
    8.4
    Accuracy
    High
  • GPT-5
    OpenAI
    V-Index
    3.68
    Cost
    $0.000225
    Quality
    9.2
    Accuracy
    High
  • Claude 4.6
    Anthropic
    V-Index
    3.13
    Cost
    $0.000270
    Quality
    9.4
    Accuracy
    High

V-Index = Quality (1–10) ÷ $/1M tokens · higher is better.Accuracy reflects model reliability for the detected task type. Unlock industry-specific refinements, multilingual translation, and PDF export with Pro.

Summary. For this creative prompt (90 tokens), DeepSeek V3.2 wins on value with a V-Index of 28.93. Quality leader: Claude 4.6. Cheapest viable: DeepSeek V3.2.

The Full Technical Audit

Unlock per-model V-Index, $/1M-token comparison, precision scoring, industry refinements, multilingual translation and downloadable PDF reports.

$9.99 / month · cancel anytime

Audit your own prompt now.

3 free audits, no signup required. Translate-to-English included for AR · HI · UR · BN · ZH.

Run a free audit

More featured audits