AsapiThe AI Agent Trials
Asapi / Catalogue / Three angled boards turned to flat outlines by a bimanual robot
Environment datasheet · Robot manipulation

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
What it tests

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.

How it works

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.

Results

All three boards came to rest outside their outlines

The dot is the one attempt.

MedianFully solved
1 modelOne attempt0%0 of 1
ModelReward
GPT‑6.1 SolOpenAI0%

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.

What models get wrong

It turns the boards but sets them down outside, then stops on the old check

Robot control

  1. All three boards came to rest outside their outlines, by 16.2, 22.7 and 43.6 mm at the worst corner.

  2. When the engine's looser check reported success, the attempt stopped, as the request said it should.

  3. It stopped after 7.6 of its 20 minutes, having sent 17 motion commands covering 85 simulated seconds.

Running it

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.