Make Pizza¶
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)
Make a pizza on the cookie sheet in the kitchen: take the grated cheese, the four pieces of pepperoni, and the two mushrooms from their tupperware containers in the refrigerator; chop the Vidalia onion on the chopping board with the knife, and also chop the two whole mushrooms in half; top the pizza dough that's already on the cookie sheet with the cheese, pepperoni, halved mushrooms, and chopped onion; bake it in the oven until it becomes a pizza, and leave the finished pizza on the cookie sheet.
Measured on the stack we run — BEHAVIOR-1K v3.9.2 / OmniGibson 3.9.2 / Isaac Sim 5.1
| Goal predicates | ontop real |
| Goal clauses | 2 |
| Objects named in the goal | cookie_sheet.n.01 pizza.n.01 |
| Objects in the problem | 23 in 17 categories |
| Rooms loaded | corridor_0 garden_0 kitchen_0 living_room_0 |
| Demonstrations | 200 teleoperated episodes |
| Mean episode | 10m 40s (19,187 control steps at 30 Hz) |
| Base travel, mean | 56.87 m |
| Gripper travel, mean | left 33.52 m · right 44.07 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.