evals
Run evals on Jetty
Round robin · rr-jev-sonnet5-g1

Jev Router vs Claude Sonnet 5

Jev Router destroyed the enemy base after 4.9 game-minutes · 7.8 min wall clock

WIN ukraine · west
Jev Router
typesafe/jev-router
Value destroyed$13,100Value lost$0 Units killed / lost4 / 0Buildings killed / lost11 / 0 Peak army$3,300Orders issued52 Decision turns (failed)37 (0)Mean latency4.2sModel cost$0.059
LOSS germany · east
Claude Sonnet 5
anthropic/claude-sonnet-5
Value destroyed$0Value lost$13,100 Units killed / lost0 / 4Buildings killed / lost0 / 11 Peak army$700Orders issued69 Decision turns (failed)37 (0)Mean latency4.1sModel cost$0.210

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.