Rubik's cube ADR robot

Closed weights OpenAI 27.8M parameters October 2019

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
OpenAI
Organisation type
Industry
Country
United States of America
Published
15 October 2019
Authors
Ilge Akkaya, Marcin Andrychowicz, Maciek Chociej, Mateusz Litwin, Bob McGrew, Arthur Petron, Alex Paino, Matthias Plappert, Glenn Powell, Raphael Ribas, Jonas Schneider, Nikolas Tezak, Jerry Tworek, Peter Welinder, Lilian Weng, Qiming Yuan, Wojciech Zaremba, Lei Zhang

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Robotics
Task
Robotic manipulation

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
27.8M

Table 13 on pg. 44 of the Cube paper, saved in "RL papers" folder. Sum of all the trainable parameters (dominated by the value and policy networks). source: https://docs.google.com/spreadsheets/d/1Kj4Q5WADcDXtUJLIOfGTCE3tGvxNczEMwyy8QtgSkHk/edit#gid=54587040&fvid=1361937389

Training data
tokens

" The cumulative amount of experience over that period used for training on the Rubik’s cube is roughly 13 thousand years, which is on the same order of magnitude as the 40 thousand years used by OpenAI Five" 13/40 * 1.92e8 = 6.24e7 EDIT 2024-05-30: OpenAI Five entry was updated in 2022 to reflect a better understanding of dataset, true size is on the order of 4.5e11 13/40 * 4.5e11 = 1.46e11

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
8.5 × 10²⁰ FLOP

source: https://docs.google.com/spreadsheets/d/1Kj4Q5WADcDXtUJLIOfGTCE3tGvxNczEMwyy8QtgSkHk/edit#gid=54587040&fvid=1361937389

How it was established
Third-party estimation

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA Tesla V100 DGXS 32 GB

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Likely
Citations
1,359

Sources

Where this record came from and when it was last checked.

Reference
Solving Rubik’s Cube with a Robot Hand
Last updated
1 January 2026

What the numbers mean

What this model is

Rubik's cube ADR robot was published by OpenAI, in United States of America, in October 2019. The organisation is categorised as industry.

It works in Robotics, and is recorded as doing robotic manipulation.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

How it was trained

Training it took roughly 8.5 × 10²⁰ FLOP of computation, on NVIDIA Tesla V100 DGXS 32 GB — a measure of what producing the model cost, not of how fast it answers.

Answers

Rubik's cube ADR robot — common questions

01

Is Rubik's cube ADR robot open source?

No. Rubik's cube ADR robot has not had its weights published, so it exists only as a service controlled by its owner.

02

How many parameters does Rubik's cube ADR robot have?

Rubik's cube ADR robot has 27.8M parameters. Table 13 on pg. 44 of the Cube paper, saved in "RL papers" folder. Sum of all the trainable parameters (dominated by the value and policy networks). source: https://docs.google.com/spreadsheets/d/1Kj4Q5WADcDXtUJLIOfGTCE3tGvxNczEMwyy8QtgSkHk/edit#gid=54587040&fvid=1361937389. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

03

Who created Rubik's cube ADR robot?

Rubik's cube ADR robot was published by OpenAI, based in United States of America, categorised as industry.

04

When was Rubik's cube ADR robot released?

Rubik's cube ADR robot was published in October 2019. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is Rubik's cube ADR robot used for?

Rubik's cube ADR robot works in Robotics, and is recorded as handling robotic manipulation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

06

How much compute was used to train Rubik's cube ADR robot?

Around 8.5 × 10²⁰ FLOP, on NVIDIA Tesla V100 DGXS 32 GB. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

07

What GPU do I need to run Rubik's cube ADR robot?

None. Rubik's cube ADR robot is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

Source

Original publication

Record last updated 1 January 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.