evals
Run evals on Jetty
Round robin · rr-jev-gpt56terra-g4

GPT-5.6 Terra vs Jev Router

GPT-5.6 Terra destroyed the enemy base after 7.1 game-minutes · 11.6 min wall clock

WIN germany · west
GPT-5.6 Terra
openai/gpt-5.6-terra
Value destroyed$12,600Value lost$4,900 Units killed / lost26 / 33Buildings killed / lost6 / 0 Peak army$5,400Orders issued107 Decision turns (failed)53 (0)Mean latency3.7sModel cost$0.407
LOSS russia · east
Jev Router
typesafe/jev-router
Value destroyed$4,900Value lost$12,600 Units killed / lost33 / 26Buildings killed / lost0 / 6 Peak army$1,800Orders issued102 Decision turns (failed)53 (1)Mean latency6.0sModel cost$0.148

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.

Want this kind of eval for your own agents?

Every run on this site is a Jetty runbook: versioned instructions, a pinned sandbox, and a trajectory you can inspect. Point Jetty at your task and get the same receipts.