evals
Run evals on Jetty

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

Claude Sonnet 5 vs Jev Router

Jev Router destroyed the enemy base after 12.4 game-minutes · 18.9 min wall clock

Pilot game (run locally, before the Jetty runs) Replay (.orarep) Decision log
LOSS russia · west
Claude Sonnet 5
anthropic/claude-sonnet-5
Value destroyed$16,100Value lost$28,950 Units killed / lost74 / 22Buildings killed / lost0 / 18 Peak army$3,550Orders issued102 Decision turns (failed)93 (0)Mean latency4.8sModel cost$0.607
WIN ukraine · east
Jev Router
typesafe/jev-router
Value destroyed$28,950Value lost$16,100 Units killed / lost22 / 74Buildings killed / lost18 / 0 Peak army$7,950Orders issued195 Decision turns (failed)93 (0)Mean latency7.4sModel cost$0.000

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 →