02 — Runs · v1 · jettyio · auto-evolved runbook (weakest-axis targeting)
opencode
google/gemini-3.5-flash
Beach scene with helmet and a basket of fish. The most illustrated of the v1 birds.
Self-score vs judge, by axis
Best round v2, 0–10 per axis
Judge: A charming white pelican with a big orange pouch, helmet and goggles sits on the seat with its wing reaching the handlebars and a fish basket; the sunset boardwalk scene is well rendered. The bicycle frame is oddly tall and stretched, with pedals and legs floating awkwardly, a strangely placed rear light beam, and a basket that obstructs the beak.
Score by round
Out of 40. Each round starts from the previous round's best SVG. Dashed line: the 28/40 pass threshold.
10 drawings, oldest first.
Click a drawing to open it in the head-to-head viewer. The outlined card is the agent's best round. Verdicts are derived (code checks on the stored SVG and judge ≥ 28/40); see Runs.
Scores per round
| Round | Pelican | Bicycle | Composition | Polish | Self total | Judge total | Verdict | Judge spread | Cost | Minutes | Trajectory |
|---|---|---|---|---|---|---|---|---|---|---|---|
| v1 | 7.7self 10 | 5.8self 10 | 7self 9.5 | 7.7self 10 | 39.5 | 28.2 | pass | 1.5 | – | – | 67836d67 |
| v2 | 8self 10 | 6.2self 10 | 7.5self 10 | 7.7self 10 | 40 | 29.3 | pass | 1 | – | – | 660d2a66 |
| v3 | 7.8self 10 | 6self 9.5 | 7.3self 9.5 | 7.5self 10 | 39 | 28.7 | pass | 1 | – | – | 5cd01e9e |
| v4 | 7.8self 10 | 6.5self 10 | 7.2self 10 | 7.5self 10 | 40 | 29 | pass | 1 | – | – | b130c9c2 |
| v5 | 7.5self 9.6 | 6.7self 9.5 | 7.3self 9.8 | 7.5self 9.7 | 38.6 | 29 | pass | 1 | – | – | d94ff2e1 |
| v6 | 7.5self 9.7 | 7.3self 9.7 | 7.8self 9.6 | 7.5self 9.7 | 38.7 | 30.2 | pass | 1 | – | – | 4a378be2 |
| v7 | 7.5self 10 | 7.3self 10 | 7.8self 10 | 7.5self 10 | 40 | 30.2 | pass | 0.5 | – | – | e3059c87 |
| v8 | 8self 9.5 | 7.5self 9.5 | 8self 9.5 | 8self 9.5 | 38 | 31.5 | pass | 0 | – | – | 70898b5c |
| v9 | 8self 9.8 | 7.7self 9.7 | 8.2self 9.7 | 7.7self 9.8 | 39 | 31.5 | pass | 1.5 | – | – | b56c0c03 |
| v10 | 7.3self 10 | 5.8self 10 | 6.8self 10 | 6.8self 10 | 40 | 26.8 | fail | 2 | – | – | 2a46de05 |