Gemini Robotics-ER 1.5
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
- Google DeepMind
- Organisation type
- Industry
- Country
- United States of America
- Published
- 25 September 2025
- Authors
- Abbas Abdolmaleki, Saminda Abeyruwan, Joshua Ainslie, Jean-Baptiste Alayrac, Montserrat Gonzalez Arenas, Ashwin Balakrishna, Nathan Batchelor, Alex Bewley, Jeff Bingham, Michael Bloesch, Konstantinos Bousmalis, Philemon Brakel, Anthony Brohan, Thomas Buschmann, Arunkumar Byravan, Serkan Cabi, Ken Caluwaerts, Federico Casarini, Christine Chan, Oscar Chang, London Chappellet-Volpini, Jose Enrique Ch…
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision, Language, Speech
- Task
- Instruction interpretation, Robotic manipulation, Image captioning, Object detection, Search, Language modeling/generation, Question answering, Speech recognition (ASR)
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
- tokens
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
- Google TPU v4,Google TPU v5e,Google TPU v6e Trillium
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
- API access
- Training code
- Unreleased
Starting today, we’re making Gemini Robotics-ER 1.5 available to developers via the Gemini API in Google AI Studio.
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
- Record confidence
- Unknown
Table 19 "Our model achieves the highest aggregated performance on 15 academic embodied reasoning benchmarks, including Point-Bench, RefSpatial, RoboSpatial-Pointing, Where2Place, BLINK, CV-Bench, ERQA, EmbSpatial, MindCube, RoboSpatial-VQA, SAT, Cosmos-Reason1, Min Video Pairs, OpenEQA and VSI-Bench."
Sources
Where this record came from and when it was last checked.
- Reference
- Gemini Robotics 1.5 brings AI agents into the physical world
- Last updated
- 28 November 2025
What the numbers mean
About this model
Gemini Robotics-ER 1.5 was published by Google DeepMind, in the country recorded as United States of America, during September 2025. The category the publisher falls under is industry.
It works in the domain of Vision, Language, Speech, and is recorded as performing the task of instruction interpretation, Robotic manipulation, Image captioning, Object detection, Search, Language modeling/generation, Question answering, Speech recognition (ASR).
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
The reason it appears in this catalogue at all: sOTA improvement.
Answers
Gemini Robotics-ER 1.5 — common questions
Gemini Robotics-ER 1.5— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
Gemini Robotics-ER 1.5— 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.
Gemini Robotics-ER 1.5— who created it?
It was published by Google DeepMind, based in United States of America, an organisation categorised as industry.
Gemini Robotics-ER 1.5— when was it released?
It was published in September 2025.
Gemini Robotics-ER 1.5— what is it used for?
It works in the domain of Vision, Language, Speech, and is recorded as handling the task of instruction interpretation, Robotic manipulation, Image captioning, Object detection, Search, Language modeling/generation, Question answering, Speech recognition (ASR). 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.
Gemini Robotics-ER 1.5— 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.
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.