Hiding Easter Eggs¶
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 BEHAVIOR-1K 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✓ 38m | 09-27 10:26 | 38m | 78 | 6.2M / 26k | $0.089 | deterministic 1, grader_error 0, instance_exact 0, instance_ok 1, n_actions 2128, video_rendered 1 |
| L✗ 4h 00m 56% | 09-27 11:55 | 4h 00m | 691 | 91.1M / 433k | $1.26 | deterministic 1, grader_error 0, live_success 0, n_actions 20172, replay_success 0, video_rendered 1 |
Task instruction (upstream)
Take the three Easter eggs out of the wicker basket on the lawn in the garden, then place them on the lawn next to a single tree (choose any tree) so that all three eggs are next to the same tree and none are left in the basket.
Measured on the stack we run — BEHAVIOR-1K v3.9.2 / OmniGibson 3.9.2 / Isaac Sim 5.1
| Goal predicates | inside nextto ontop |
| Quantifiers | exists forall |
| Goal clauses | 2 |
| Objects named in the goal | easter_egg.n.01 lawn.n.01 tree.n.01 wicker_basket.n.01 |
| Objects in the problem | 8 in 5 categories |
| Rooms loaded | corridor_0 garden_0 kitchen_0 living_room_0 |
| Demonstrations | 200 teleoperated episodes |
| Mean episode | 4m 14s (7,620 control steps at 30 Hz) |
| Base travel, mean | 21.9 m |
| Gripper travel, mean | left 10.72 m · right 12.23 m |
| Evaluation instances | 20 public test instances (ids 301–320) |
Read from BDDL activity definitions + 2026-challenge-task-instances (licensed download), 2026-09-21.
Tags¶
Why this task is interesting¶
Not yet written.
Capability notes¶
Not yet written.
Oracle demo review¶
Not yet reviewed.