---
title: "Investigations: what the Micropolis runs show | Evals by Jetty"
url: https://evaljetty.com/micropolis/investigations/
description: "Which model plans a city best, which SimCity scenarios break which models, and is the expensive model worth it: answered from the stored Micropolis runs."
updated: 2026-09-28
publisher: Jetty (https://jetty.io)
---

03 — Investigations

# Questions answered from the runs.

One question each, answered from the Round 1 runs.

[Compare setups

### Which model plans a city best?

Jev Router built the largest cities (mean 12,120 people after 20 years), ahead of GPT-5.6 Luna (7,210), GPT-5.6 Terra (3,290) and Claude Sonnet 5 (1,070). With two maps per model, the order is a signal, not a verdict.](https://evaljetty.com/micropolis/investigations/which-model.html)[Break down by case

### Which scenarios break which models?

Scenario wins: Tokyo 1957 1/8; San Francisco 1906 0/8; Detroit 1972 0/8. Best at recovery: GPT-5.6 Terra (1/6).](https://evaljetty.com/micropolis/investigations/scenarios.html)[Is it worth the cost?

### Is the expensive model worth it?

GPT-5.6 Terra met goals for the least money ($7.55 per goal met); per-run cost ranged from $0.08 (GPT-5.6 Luna) to $1.76 (Jev Router).](https://evaljetty.com/micropolis/investigations/cost-vs-outcome.html)

---
Source: https://evaljetty.com/micropolis/investigations/ · Evals by Jetty · Run your own evals: https://jetty.io/?utm_source=evaljetty&utm_medium=llms