evals
Run evals on Jetty
Round robin · rr-jev-sonnet5-g3

Jev Router vs Claude Sonnet 5

Jev Router destroyed the enemy base after 5.6 game-minutes · 7.7 min wall clock

WIN germany · west
Jev Router
typesafe/jev-router
Value destroyed$13,500Value lost$700 Units killed / lost7 / 5Buildings killed / lost8 / 0 Peak army$2,500Orders issued62 Decision turns (failed)42 (0)Mean latency4.5sModel cost$0.081
LOSS germany · east
Claude Sonnet 5
anthropic/claude-sonnet-5
Value destroyed$700Value lost$13,500 Units killed / lost5 / 7Buildings killed / lost0 / 8 Peak army$2,100Orders issued80 Decision turns (failed)42 (0)Mean latency4.8sModel cost$0.263

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.