02 — Run · Round 1 · vs OpenRA AI · ladder-gpt56terra-beginner-g1
GPT-5.6 Terra vs OpenRA AI (Beginner)
OpenRA AI (Beginner) won on score at the time limit (34,750 to 27,700) after 20.0 game-minutes · 22.8 min wall clock
LOSS ukraine · west
GPT-5.6 Terra
openai/gpt-5.6-terra
Value destroyed$7,600Value lost$27,600
Units killed / lost31 / 87Buildings killed / lost4 / 0
Peak army$4,650Orders issued126
Decision turns (failed)151 (0)Mean latency3.8sModel cost$1.211
WIN ukraine · east
OpenRA AI (Beginner)
openra/beginner-ai
Value destroyed$27,600Value lost$7,600
Units killed / lost87 / 31Buildings killed / lost0 / 4
Peak army$0Orders issued51
Decision turns (failed)0 (0)Mean latency–Model cost$0.000
Evaluation
passchecks 7/7 verdict computed from the gating checks
Round-1 run: written before the runbook moved to evals v2, so these are the older self-reported checks.
| Status | Kind | Check | Detail |
|---|---|---|---|
| pass | code_check | result-json | result json |
| pass | code_check | has-winner | has winner |
| pass | code_check | decisions-logged | decisions logged |
| pass | code_check | replay-saved | replay saved |
| pass | code_check | video-rendered | video rendered |
| pass | code_check | no-llm-outage | no llm outage |
| pass | code_check | video-complete | video complete |
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.