Sorting Vegetables¶
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
Not in this run: not among the 30 chosen for the first round (2026-09-26): mostly particles, cutting and liquids, or long tidy-ups like chosen ones
Task instruction (upstream)
Sort the vegetables from the two wicker baskets on the kitchen floor into the mixing bowls on the kitchen countertop: put all three bok choy and all three Vidalia onions together into one mixing bowl; put both leeks and both broccoli together into a second mixing bowl; and put all three sweet corn into a third mixing bowl.
Measured on the stack we run — BEHAVIOR-1K v3.9.2 / OmniGibson 3.9.2 / Isaac Sim 5.1
| Goal predicates | inside |
| Quantifiers | exists forall |
| Goal clauses | 3 |
| Objects named in the goal | bok_choy.n.02 broccoli.n.02 leek.n.02 mixing_bowl.n.01 sweet_corn.n.02 vidalia_onion.n.01 |
| Objects in the problem | 21 in 10 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 37s (11,904 control steps at 30 Hz) |
| Base travel, mean | 33.95 m |
| Gripper travel, mean | left 46.3 m · right 22.88 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.