evals
Create your eval

02 — Run · Round 1 · Detroit 1972: crime · jev-detroit-s1

Jev Router plays Detroit 1972

Detroit's crime is out of control in 1972. Bring average crime under 60 in 10 years, without emptying the city. Ended Jan 1982: lost, city score 595.

GOAL MISSED seed 1
Jev Router
typesafe/jev-router

LOST: Average crime 22 (goal < 60), population 7,380 (floor 25,000); engine verdict: won

Population (start → end)76,160 → 7,380 Peak population76,160City score (start → end)285 → 595 Funds at the end$0Crime / pollution / traffic22 / 47 / 0 Zones R / C / I129 / 66 / 86 Power plants (coal / nuclear)2 / 3Police / fire stations16 / 6 Turns (model / failed)40 (40 / 3) Actions applied / rejected109 / 6 Mean turn latency39.2sModel cost$2.206Wall clock26.2 min Jetty run IDaea16d25

The city over time

Population

People, after every turn

Funds

Treasury, after every turn

City score

0–1000, re-evaluated each January

Table view
TurnDatePopulationFundsCity scoreCrimePollution
0Jan 197276,160$20,0002859264
1Apr 197274,260$17,4705399264
2Jul 197270,980$14,9205397763
3Oct 197265,840$14,9155397961
4Jan 197359,380$10,8224837961
5Apr 197354,380$10,6834837059
6Jul 197349,340$10,6834836659
7Oct 197344,920$10,1594836659
8Jan 197438,120$8,0043904958
9Apr 197433,820$8,0043904255
10Jul 197430,180$8,0043904250
11Oct 197426,900$8,0043903850
12Jan 197524,240$6,6373833449
13Apr 197523,140$6,6373833448
14Jul 197521,320$6,6373833248
15Oct 197520,120$6,6373833048
16Jan 197618,580$5,0514063047
17Apr 197617,020$5,0514062848
18Jul 197616,020$4,9664062748
19Oct 197614,940$4,9364062747
20Jan 197713,600$4,2823912648
21Apr 197712,480$4,2823912548
22Jul 197712,900$4,2823912546
23Oct 197713,020$3,9713912445
24Jan 197813,040$2,8835152445
25Apr 197810,880$2,8835152446
26Jul 19789,320$2,6805152245
27Oct 19788,540$2,6805152047
28Jan 19797,540$9024092047
29Apr 19795,780$8064091952
30Jul 19795,300$8064091951
31Oct 19795,240$8064091951
32Jan 19804,740$2913671952
33Apr 19804,220$2913671850
34Jul 19803,920$2913671851
35Oct 19804,820$2913671851
36Jan 19818,840$1316831947
37Apr 19819,920$1316831950
38Jul 19818,980$1316832250
39Oct 19818,160$1316832249
40Jan 19827,020$05952247

Final map

Final city map: Jev Router on Detroit 1972: crime

Evaluation

failchecks 9/10 verdict: valid run (code checks and checklist) and task goal met (judge)

StatusKindCheckDetail
passstepenvironmentEnvironment check (snapshot, engine, key)
passsteplaunchLaunch run-city as a detached process
passstepsuperviseSupervise in the foreground until run-city exits
passsteprenderTimelapse video rendered
passstepnotesAppend Notes to summary.md
passcode_checkoutputs-existall present
passcode_checksim-reached-deadlineended Jan 1982 after 40 turns; scenario verdict True
passcode_checkdecisions-logged40 rows for 40 turns
passcode_checkllm-turns-valid3/40 model turns failed
passcode_checkvideo-decodesduration 36.9s
passcode_checklimits-respected26.2 wall-minutes (model budget 45.0 min)
failjudgescenario-goalLOST: Average crime 22 (goal < 60), population 7,380 (floor 25,000); engine verdict: won (score 0 / threshold 1)
passchecklistnotes-explain-outcomesummary.md has a Notes section citing model thoughts from turns 1, 8, and 40 explaining crime success and population collapse
passchecklistplayer-matches-requestresult.json shows player=jev, task=detroit, seed=1 matching the requested parameters
passchecklistno-silent-outage3 of 40 turns failed (turns 28 and 30 were timeouts), all within the 20% threshold; no long consecutive failure stretch

Decision timeline

What the mayor thought and did each turn. Click a turn to jump the timelapse there.

Ready to stop guessing if your outputs are good?

Create your eval Book a 15-minute walkthrough
Connect your agent to Jetty →