evals
Run evals on Jetty
Pilot cup · cup1-final-g1

Jev Router vs Claude Sonnet 5

Claude Sonnet 5 destroyed the enemy base after 7.3 game-minutes · 12.1 min wall clock

Pilot game (run locally, before the Jetty runs) Replay (.orarep) Decision log Runtime config
LOSS england · west
Jev Router
typesafe/jev-router
Value destroyed$2,000Value lost$17,000 Units killed / lost20 / 47Buildings killed / lost0 / 11 Peak army$3,200Orders issued136 Decision turns (failed)55 (0)Mean latency8.3sModel cost$0.000
WIN ukraine · east
Claude Sonnet 5
anthropic/claude-sonnet-5
Value destroyed$17,000Value lost$2,000 Units killed / lost47 / 20Buildings killed / lost11 / 0 Peak army$6,500Orders issued179 Decision turns (failed)55 (0)Mean latency4.6sModel cost$0.365

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.