Student of Games

Closed weights DeepMind December 2021

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
DeepMind
Organisation type
Industry
Country
United Kingdom of Great Britain and Northern Ireland
Published
6 December 2021
Authors
Martin Schmid, Matej Moravcik, Neil Burch, Rudolf Kadlec, Josh Davidson, Kevin Waugh, Nolan Bard, Finbarr Timbers, Marc Lanctot, Zach Holland, Elnaz Davoodi, Alden Christianson, Michael Bowling

What it does

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

Domain
Games
Task
Chess, Go, Poker

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.

Training data
245,760,000,000 tokens

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
3.7 × 10²² FLOP

"We trained a version of AlphaZero using its original settings in chess and Go, e.g. , using 800 MCTS simulations during training, with 3500 concurrent actors each on a single TPUv4, for a total of 800k training steps. SOG was trained using a similar amount of TPU resources."

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.

Why it is tracked
SOTA improvement

"Player of Games reaches strong performance in chess and Go, beats the strongest openly available agent in heads-up no-limit Texas hold'em poker (Slumbot), and defeats the state-of-the-art agent in Scotland Yard"

Record confidence
Speculative
Citations
32

Sources

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

Reference
Player of Games
Last updated
25 May 2026

What the numbers mean

About this model

Student of Games was published by DeepMind, in the country recorded as United Kingdom of Great Britain and Northern Ireland, during December 2021. It comes out of an organisation categorised as industry.

It works in the domain of Games, and is recorded as performing the task of chess, Go, Poker.

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 a computation budget of roughly 3.7 × 10²² FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The training set ran to roughly 245,760,000,000 tokens of text.

The reason it appears in this catalogue at all: sOTA improvement.

Answers

Student of Games — common questions

01

Student of Games— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

02

Student of Games— how many parameters does it have?

No parameter count has been published for it, which is why no memory or speed figure appears on this page.

03

Student of Games— who created it?

It was published by DeepMind, based in United Kingdom of Great Britain and Northern Ireland, an organisation categorised as industry.

04

Student of Games— when was it released?

It was published in December 2021. 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

Student of Games— what is it used for?

It works in the domain of Games, and is recorded as handling the task of chess, Go, Poker. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

06

Student of Games— how much compute was used to train it?

Training consumed around 3.7 × 10²² FLOP. 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

Student of Games— what GPU do I need to run it?

None. This 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 25 May 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.