Tidying Living Room¶
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 20:03 | 4h 00m | 583 | 74.7M / 339k | $1.04 | grader_error 0, missing_trajectory 1 |
| L✗ 3h 52m 0% | 09-27 15:39 | 3h 52m | 526 | 68.2M / 287k | $0.911 | deterministic 1, grader_error 0, live_success 0, n_actions 6804, replay_success 0, video_rendered 1 |
No instruction published upstream
The 2025 carryover tasks ship without instruction text. Watch the demo and write the goal in your own words below, clearly marked as a reconstruction rather than the official goal.
Measured on the stack we run — BEHAVIOR-1K v3.9.2 / OmniGibson 3.9.2 / Isaac Sim 5.1
| Goal predicates | inside ontop |
| Quantifiers | exists |
| Goal clauses | 4 |
| Objects named in the goal | bookcase.n.01 coffee_table.n.01 desk.n.01 hardback.n.01 newspaper.n.03 notebook.n.01 pot_plant.n.01 |
| Objects in the problem | 9 in 9 categories |
| Rooms loaded | living_room_0 |
| Demonstrations | 200 teleoperated episodes |
| Mean episode | 6m 59s (12,566 control steps at 30 Hz) |
| Base travel, mean | 20.65 m |
| Gripper travel, mean | left 18.47 m · right 18.56 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.