Putting Dishes Away After Cleaning¶
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✗ 4h 00m 0% | 09-27 22:38 | 4h 00m | 628 | 79.8M / 367k | $1.13 | grader_error 0, missing_trajectory 1 |
| L✗ 4h 00m 0% | 09-28 02:27 | 4h 00m | 624 | 80.9M / 310k | $1.09 | deterministic 1, grader_error 0, live_success 0, n_actions 6569, replay_success 0, video_rendered 1 |
Task instruction (upstream)
In the kitchen, gather all eight plates from the two countertops, place them all inside a single cabinet (either one), and make sure all cabinets are closed when you're done.
Measured on the stack we run — BEHAVIOR-1K v3.9.2 / OmniGibson 3.9.2 / Isaac Sim 5.1
| Goal predicates | inside open |
| Quantifiers | exists forall |
| Goal clauses | 2 |
| Objects named in the goal | cabinet.n.01 plate.n.04 |
| Objects in the problem | 14 in 5 categories |
| Rooms loaded | corridor_0 dining_room_0 entryway_0 garden_0 kitchen_0 living_room_0 living_room_1 |
| Demonstrations | 200 teleoperated episodes |
| Mean episode | 6m 05s (10,953 control steps at 30 Hz) |
| Base travel, mean | 33.05 m |
| Gripper travel, mean | left 28.34 m · right 31.51 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¶
Task DomainMobile / Whole-body Manipulation
Why this task is interesting¶
Not yet written.
Capability notes¶
Not yet written.
Oracle demo review¶
Not yet reviewed.