evals
Run evals on Jetty

02 — Run · Round 2 · Round robin · r2-rr-jev-gpt56terra-g4

GPT-5.6 Terra vs Jev Router

Jev Router destroyed the enemy base after 9.3 game-minutes · 14.9 min wall clock

LOSS england · west
GPT-5.6 Terra
openai/gpt-5.6-terra
Value destroyed$4,100Value lost$16,700 Units killed / lost21 / 30Buildings killed / lost1 / 8 Peak army$2,000Orders issued65 Decision turns (failed)70 (0)Mean latency3.4sModel cost$0.493
WIN france · east
Jev Router
typesafe/jev-router
Value destroyed$16,700Value lost$4,100 Units killed / lost30 / 21Buildings killed / lost8 / 1 Peak army$7,900Orders issued157 Decision turns (failed)70 (2)Mean latency5.5sModel cost$0.129

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': 70, 'Multi1': 70}
passcode_checkllm-turns-validfailed/total per slot: {'Multi0': '0/70', 'Multi1': '0/70'}
passcode_checkvideo-decodesduration 94.6s
passcode_checkvideo-completevideo ends at tick 13886 of 13886
passcode_checklimits-respectedended after 14.9 wall-minutes (budget 30.0 min): base destroyed
passchecklistnotes-explain-winNotes section cites both models final thoughts and explains Jev Router won via superior army build and income management
passchecklistplayers-match-requestresult.json records gpt56terra as Multi0 and jev as Multi1 matching the requested players
passchecklistno-silent-outagerun.log shows continuous turn lines with no gaps, 0 failures for both models across all 70 turns

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 →