evals
Run evals on Jetty

02 — Run · Round 2 · Round robin · r2-rr-jev-gpt56luna-g3

Jev Router vs GPT-5.6 Luna

Jev Router destroyed the enemy base after 5.4 game-minutes · 7.9 min wall clock

WIN germany · west
Jev Router
typesafe/jev-router
Value destroyed$10,500Value lost$300 Units killed / lost24 / 3Buildings killed / lost6 / 0 Peak army$3,300Orders issued63 Decision turns (failed)41 (0)Mean latency4.4sModel cost$0.070
LOSS france · east
GPT-5.6 Luna
openai/gpt-5.6-luna
Value destroyed$300Value lost$10,500 Units killed / lost3 / 24Buildings killed / lost0 / 6 Peak army$2,300Orders issued77 Decision turns (failed)41 (0)Mean latency3.3sModel cost$0.030

Evaluation

passchecks 10/10 verdict computed from the gating checks

StatusKindCheckDetail
passstepenvironmentEnvironment check (snapshot, engine, content, key)
passsteplaunchLaunch run-match as a detached process
passstepsuperviseSupervise in the foreground until run-match exits
passsteprenderRender the 1080p recording
passstepnotesAppend Notes to summary.md
passcode_checkoutputs-existall present
passcode_checkgame-has-winnerjev won: base destroyed
passcode_checkdecisions-loggedturns per slot: {'Multi0': 41, 'Multi1': 41}
passcode_checkllm-turns-validfailed/total per slot: {'Multi0': '0/41', 'Multi1': '0/41'}
passcode_checkvideo-decodesduration 55.8s
passcode_checkvideo-completevideo ends at tick 8068 of 8068
passcode_checklimits-respectedended after 7.9 wall-minutes (budget 30.0 min): base destroyed
passchecklistnotes-explain-winNotes section explains Jev Router dominated via superior army and economy, cites both models final thoughts
passchecklistplayers-match-requestresult.json shows Multi0=jev (Jev Router/typesafe/jev-router) and Multi1=gpt56luna (GPT-5.6 Luna/openai/gpt-5.6-luna) as requested
passchecklistno-silent-outagerun.log shows 41 consecutive decision turns for both players with no gaps or repeated failures

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 →