Three angled boards turned to flat outlines by a bimanual robot
ID llarms/task02 · revision 2 · results as of 29 October 2026
In a simulated robot workshop, the agent drives a two‑handed robot by typed commands to lift three boards from angled cradles, turn each to lie flat, and let it settle exactly inside its outline.
- Checks
- 1, 1 point for the whole build, none for part of it
- Tested
- 1 model, one attempt
- Best
- 0% (GPT‑6.1 Sol)
- Full solves
- 0 of 1
- Attempt
- 8 min
Three boards lifted from angled cradles, turned flat and set in their outlines
Robot control
Each board must come out of its angled cradle, turn about up to three axes and settle flat inside its outline, all three stable together.
A simulated workshop, two five‑fingered hands and three angled boards
The agent's world
A coding agent sends JSON to a local robot server: read the state, or send a motion of 1 to 32 velocity segments.
The robot
Two seven‑joint manipulators on sliding bases, each with a five‑fingered hand that holds by friction alone, so boards can slip, turn or drop.
Limits
One session of 20 minutes of wall time, planning included, with action and simulation‑time budgets; no resets or direct state changes.
The reward
One point only if all three boards settle with every corner inside an outline of their own size, after being grasped and released.
All three boards came to rest outside their outlines
The dot is the one attempt.
| Model | Reward |
|---|---|
| GPT‑6.1 SolOpenAI | 0% |
This attempt was told an earlier, looser target that accepted boards centimetres off, and not the corner rule; its score uses the strict outlines. A person can complete this build easily.
It turns the boards but sets them down outside, then stops on the old check
Robot control
All three boards came to rest outside their outlines, by 16.2, 22.7 and 43.6 mm at the worst corner.
When the engine's looser check reported success, the attempt stopped, as the request said it should.
It stopped after 7.6 of its 20 minutes, having sent 17 motion commands covering 85 simulated seconds.
What an attempt takes, and what the environment includes
An attempt
Cost and tokens weren't recorded: the attempt ran on a subscription sign‑in, which logs neither.
What's in it
The frozen runtime with this scenario, the request and interface document, the grader and its self‑test, and the attempt's full record and videos.
Format
Node.js, with the physics in headless Edge and a Python grader; it runs on a Windows PC today, and other packaging is on request.
Fresh variants
Other builds and layouts in the same design, made on request and never published.
The files and grader aren't published; the job's row on The AI Agent Trials, our public benchmark, sums up the job and shows each model's score.
Try one of our three sample environments
Three environments are packaged as samples you can download, with their graders and reference solutions. Ask for them with your work email, or book a call about the rest of the catalogue.
AsapiThe AI Agent Trials