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.
Break down by caseWhich 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).
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).