evals
Run evals on Jetty

02 — Run · Pilot cup · Pilot cup · cup1-sf1-g2

GPT-5.6 Terra vs Jev Router

Jev Router won on score at the time limit (48,150 to 33,800) after 14.0 game-minutes · 28.1 min wall clock

Pilot game (run locally, before the Jetty runs) Replay (.orarep) Decision log
LOSS germany · west
GPT-5.6 Terra
openai/gpt-5.6-terra
Value destroyed$22,200Value lost$25,800 Units killed / lost99 / 122Buildings killed / lost2 / 1 Peak army$3,600Orders issued165 Decision turns (failed)106 (0)Mean latency3.7sModel cost$0.834
WIN england · east
Jev Router
typesafe/jev-router
Value destroyed$25,800Value lost$22,200 Units killed / lost122 / 99Buildings killed / lost1 / 2 Peak army$4,200Orders issued192 Decision turns (failed)106 (1)Mean latency11.1sModel cost$0.009

Evaluation

No validation report stored for this run.

Decision timeline

What each model saw as its situation and what it ordered, every 8 game-seconds. Click a turn to jump the video there.

Ready to stop guessing if your outputs are good?

Get Started Book a 15-minute walkthrough
Connect your agent to Jetty →