Oil · Cypresses¶
Agent runs
Each mode of this task runs once per run. Est. cost is tokens at list price (data/prices.yml), never a bill; see the RoboPaint runs for every task of a run.
Codex + GPT-6 Luna, reasoning xhigh (ChatGPT login)default run
| Trial | Started | Agent time | Model requests | Tokens in / out | Est. cost | Grade |
|---|---|---|---|---|---|---|
| U✓ 1h 09m | 09-28 13:02 | 1h 09m | 105 | 11.4M / 84k | $0.175 | deterministic 1, grader_error 0, instance_exact 1, instance_ok 1, missing_trajectory 0, n_actions 65127, video_rendered 1 |
| L✗ 41m 43% | 09-29 14:35 | 41m | 84 | 7.6M / 92k | $0.139 | deterministic 1, grader_error 0, instance_exact 1, n_actions 43290, replay_success 0, video_rendered 1 |
Task instruction (upstream)
Paint the picture shown in /app/target.png (a square crop of Vincent van Gogh's Wheat Field with Cypresses, 1889) onto the main sheet with brush and oil paints, in at most 419 strokes.
Playback speed
Recorded by us: our reference solution, replayed by the verifier (canvas camera, scene camera, side camera, exact canvas).
What RoboPaint states about this task
| Success criteria | 1. scored at a 1 mm scale against the picture, all after the best single shift of the sheet, at most 5 mm along each axis, inside the central area 8 mm in from the sheet's edges 2. mean CIELAB ΔE <= 9.7 3. p90 ΔE <= 17.5 4. SSIM of L* >= 0.56 5. edge correlation >= 0.43 6. paint IoU >= 0.96 7. at most 419 strokes 8. both fresh-process replays of the trajectory meet this and end in the same state |
| Family | oil |
| Picture | a square crop of Vincent van Gogh's Wheat Field with Cypresses, 1889 |
| Difficulty | extreme |
| Tier | privileged |
| Continuous Score | 1 - mean ΔE / 20 |
| Grader Facts | name — cypresses alpha — truth_alpha.npz n_strokes — 279 source — the reference picture: File:Vincent van Gogh - Wheat Field with Cypresses - Google Art Project.jpg (public domain), cropped and downscaled license — Public domain area_mm2 — 51612.8 |
| Scoring | s.score() is served by a separate scoring container: it replays the actions the agent executed since its last reset on the graders' copy and returns the metrics, never images or target data |
| Agent Budget | 7200 s of wall clock per mode |
From our RoboPaint task definitions.
Tags¶
Task DomainManipulation
Why this task is interesting¶
Not yet written.
Capability notes¶
Not yet written.
Oracle demo review¶
Not yet reviewed.