DASHBOARD · DATA · every model, same prompt

Model 3 pricing strategies

11 models built this from the identical prompt. Click any one to open the live build.

Opus 4.8 · pickopen →
GPT-5.5open →
Gemini 3.5open →
Grok 4.3open →
GLM 5.2open →
Qwen 3.7open →
DeepSeek V4open →
Mistral Largeopen →
Kimi K2.7open →
MiniMax M3open →
GPT-OSS 120bopen →
▸ The prompt every model got
You're the founder of a B2B SaaS (a project-management tool) deciding between three pricing strategies for next year. Build an interactive pricing model in a single self-contained HTML file.

Your raw data is the attached file saas-customers.csv — 1,620 rows, one per customer (1,200 active + 420 already churned): tier, seats_licensed, seats_active_30d, list_mrr, net_mrr, discount, months_since_signup, expansions, expansion_mrr, days_since_last_login, acq_channel, industry, region, status, churn_month. Derive your current-state metrics from this data yourself — total MRR, customers + MRR by tier, churn rate by tier (use the churned rows), expansion behavior, and any at-risk segments (low logins, heavy discounts).

Model these three strategies for the next 24 months, vs a do-nothing baseline:
- A - Raise all prices 25%. Assume churn rises +0.8pp on Starter, +0.4pp on Pro, no change on Business, and new-customer conversion drops 10%.
- B - Add a usage-based add-on ($0.40 per project over 20). Assume 35% of Pro + Business adopt it at ~$22/mo extra; no churn change.
- C - Repackage: kill Starter and force-migrate those customers to a new $49 'Team' tier. Assume 30% churn on the forced migration; the rest convert.

Build a single self-contained HTML page that:
1. Projects MRR and ARR over 24 months for each strategy + the baseline (chart).
2. Shows a revenue waterfall (new / expansion / contraction / churn) for each strategy.
3. Has a side-by-side comparison and a table of ending ARR, total churned MRR, and blended ARPU.
4. Has sliders for the churn deltas, expansion rate, new-customer growth, and add-on adoption %.
5. Names the winning strategy and the trade-offs.

Vanilla JS + inline SVG or <canvas> for charts, no external libraries. Return only the HTML.