OpenAI Five Rerun

Closed weights OpenAI 159M parameters December 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
13 December 2019
Authors
Christopher Berner, Greg Brockman, Brooke Chan, Vicki Cheung, Przemysław “Psyho" Dębiak, Christy Dennison, David Farhi, Quirin Fischer, Shariq Hashme, Chris Hesse, Rafal Józefowicz, Scott Gray, Catherine Olsson, Jakub Pachocki, Michael Petrov, Henrique Pondé de Oliveira Pinto, Jonathan Raiman, Tim Salimans, Jeremy Schlatter, Jonas Schneider, Szymon Sidor, Ilya Sutskever, Jie Tang, Filip Wolski, Su…

What it does

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

Domain
Games
Task
Dota 2
Approach
Self-supervised learning

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
159M

"We define a policy (π) as a function from the history of observations to a probability distribution over actions, which we parameterize as a recurrent neural network with approximately 159 million parameters (θ)." pg. 3 of paper source: https://docs.google.com/spreadsheets/d/1Kj4Q5WADcDXtUJLIOfGTCE3tGvxNczEMwyy8QtgSkHk/edit#gid=54587040&fvid=1361937389

Training data
53,084,160,000 tokens

54k iterations (Fig 7) with a batch size of 983040 (Table 2)

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
1.3 × 10²² FLOP

THIS CALCULATION IS FOR RERUN "Rerun took 2 months and 150 ± 5 PFlops/s·days of compute (see Figure 4)" 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 P100
Chips used
512
Power draw
262.1 kW
Compute cost
$321,106

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
Highly cited,SOTA improvement

"On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game."

Record confidence
Confident
Citations
2,137

Sources

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

Reference
Dota 2 with Large Scale Deep Reinforcement Learning
Last updated
25 May 2026

What the numbers mean

What this model is

OpenAI Five Rerun was published by OpenAI, in United States of America, in December 2019. The organisation is categorised as industry.

It works in Games, and is recorded as doing dota 2.

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

Training and provenance

Training it took roughly 1.3 × 10²² FLOP of computation, on NVIDIA P100 — a measure of what producing the model cost, not of how fast it answers.

It was trained on about 53,084,160,000 tokens of text.

Its inclusion criterion is highly cited,SOTA improvement.

Answers

OpenAI Five Rerun — common questions

01

When was OpenAI Five Rerun released?

OpenAI Five Rerun was published in December 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.

02

What is OpenAI Five Rerun used for?

OpenAI Five Rerun works in Games, and is recorded as handling dota 2. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

03

How much compute was used to train OpenAI Five Rerun?

Around 1.3 × 10²² FLOP, on NVIDIA P100. 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.

04

What GPU do I need to run OpenAI Five Rerun?

None. OpenAI Five Rerun 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.

05

Is OpenAI Five Rerun open source?

No. OpenAI Five Rerun has not had its weights published, so it exists only as a service controlled by its owner.

06

How many parameters does OpenAI Five Rerun have?

OpenAI Five Rerun has 159M parameters. "We define a policy (π) as a function from the history of observations to a probability distribution over actions, which we parameterize as a recurrent neural network with approximately 159 million parameters (θ)." pg. 3 of paper 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.

07

Who created OpenAI Five Rerun?

OpenAI Five Rerun was published by OpenAI, based in United States of America, categorised as industry.

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.