evals
Create your eval

02 — Run · Round 2 · Round robin · r2-rr-gpt56terra-gpt6luna-g2

GPT-6 Luna vs GPT-5.6 Terra

GPT-5.6 Terra destroyed the enemy base after 4.2 game-minutes · 7.3 min wall clock

LOSS russia · west
GPT-6 Luna
openai/gpt-6-luna
Value destroyed$100Value lost$8,300 Units killed / lost1 / 13Buildings killed / lost0 / 5 Peak army$1,300Orders issued33 Decision turns (failed)32 (0)Mean latency3.1sModel cost$0.010
WIN ukraine · east
GPT-5.6 Terra
openai/gpt-5.6-terra
Value destroyed$8,300Value lost$100 Units killed / lost13 / 1Buildings killed / lost5 / 0 Peak army$5,900Orders issued72 Decision turns (failed)32 (0)Mean latency3.5sModel cost$0.218

Evaluation

passchecks 7/7 verdict computed from the gating checks

StatusKindCheckDetail
passsteplaunchLaunch run-match as a detached process
passstepsuperviseSupervise in the foreground until run-match exits
passsteprenderRender the 1080p recording
passcode_checkoutputs-existall present
passcode_checkgame-has-winnergpt56terra won: base destroyed
passcode_checkdecisions-loggedturns per slot: {'Multi0': 32, 'Multi1': 32}
passcode_checkllm-turns-validfailed/total per slot: {'Multi0': '0/32', 'Multi1': '0/32'}
passcode_checkvideo-decodesduration 43.9s
passcode_checkvideo-completevideo ends at tick 6279 of 6279
passcode_checklimits-respectedended after 7.3 wall-minutes (budget 30.0 min): base destroyed

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?

Create your eval Book a 15-minute walkthrough
Connect your agent to Jetty →