Tidying Bedroom¶
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✓ 2h 35m | 09-27 23:31 | 2h 35m | 358 | 45.8M / 146k | $0.603 | deterministic 1, grader_error 0, instance_exact 1, instance_ok 1, n_actions 3242, video_rendered 1 |
| L✗ 4h 00m 0% | 09-28 02:40 | 4h 00m | 708 | 91.3M / 327k | $1.22 | deterministic 1, grader_error 0, live_success 0, n_actions 8068, replay_success 0, video_rendered 1 |
Task instruction (upstream)
In the bedroom, move the book from the bed onto either nightstand, and place the two sandals side by side next to the bed.
Measured on the stack we run — BEHAVIOR-1K v3.9.2 / OmniGibson 3.9.2 / Isaac Sim 5.1
| Goal predicates | nextto ontop |
| Quantifiers | exists |
| Goal clauses | 3 |
| Objects named in the goal | bed.n.01 book.n.02 sandal.n.01 table.n.02 |
| Objects in the problem | 8 in 6 categories |
| Rooms loaded | bathroom_1 bedroom_0 corridor_0 dining_room_0 entryway_0 garden_0 |
| Demonstrations | 200 teleoperated episodes |
| Mean episode | 6m 08s (11,037 control steps at 30 Hz) |
| Base travel, mean | 33.4 m |
| Gripper travel, mean | left 12.65 m · right 12.59 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.