evals
Run evals on Jetty

02 — Run · Round 2 · Round robin · r2-rr-gpt56terra-gpt56luna-g2

GPT-5.6 Luna vs GPT-5.6 Terra

GPT-5.6 Terra destroyed the enemy base after 5.9 game-minutes · 7.7 min wall clock

LOSS russia · west
GPT-5.6 Luna
openai/gpt-5.6-luna
Value destroyed$2,600Value lost$9,600 Units killed / lost20 / 15Buildings killed / lost0 / 6 Peak army$1,700Orders issued69 Decision turns (failed)45 (0)Mean latency3.2sModel cost$0.034
WIN russia · east
GPT-5.6 Terra
openai/gpt-5.6-terra
Value destroyed$9,600Value lost$2,600 Units killed / lost15 / 20Buildings killed / lost6 / 0 Peak army$4,000Orders issued84 Decision turns (failed)45 (0)Mean latency3.4sModel cost$0.322

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-winnergpt56terra won: base destroyed
passcode_checkdecisions-loggedturns per slot: {'Multi0': 45, 'Multi1': 45}
passcode_checkllm-turns-validfailed/total per slot: {'Multi0': '0/45', 'Multi1': '0/45'}
passcode_checkvideo-decodesduration 60.7s
passcode_checkvideo-completevideo ends at tick 8801 of 8801
passcode_checklimits-respectedended after 7.7 wall-minutes (budget 30.0 min): base destroyed
passchecklistnotes-explain-winsummary.md Notes section cites final thoughts from both models and explains Terra won via economic dominance and base destruction
passchecklistplayers-match-requestresult.json records gpt56luna as Multi0 and gpt56terra as Multi1 exactly as requested
passchecklistno-silent-outagerun.log shows uninterrupted decision turns with 0 LLM failures across all 45 turns per player

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 →