---
title: "RT-2 | Vision-Language-Action Model | world-models.io"
canonical: "https://world-models.io/en/models/rt-2/"
description: "RT-2 is Google DeepMind's Vision-Language-Action model that transfers web-scale knowledge to robotic control."
author: "Tyler D."
generated: "2026-10-30"
---

New: the Timeline is live. Track world model releases, papers, and benchmark updates in real time.

The Knowledge Hub for AI World Models

# RT-2

RT-2 (Robotic Transformer 2) is a Vision-Language-Action model by Google DeepMind that transfers knowledge from web-scale vision-language pretraining directly to robotic control policies.

robotics

model-based-rl

simulation

embodied-ai

## What is a world model?

A world model is an AI system that learns a predictive representation of how an environment changes over time. It can use observations, actions, or language to estimate future states and possible outcomes before an agent acts. World models support planning in model-based reinforcement learning, robotics, embodied AI, autonomous driving, and interactive simulation. This site catalogs these systems with model records, research papers, benchmark context, and source links. Start with the [world models database](https://world-models.io/en/world-models-database/), compare systems on the [leaderboard](https://world-models.io/en/leaderboard/), or read the [Performance Index methodology](https://world-models.io/en/methodology/performance-index/).

## Key Attributes

Static HTML snapshot of the model record for crawlers and no-JS readers.

| Attribute | Value |
| --- | --- |
| Model | RT-2 |
| Lab / Organization | DeepMind |
| Category | Foundation World Model |
| Subtype | Vision-Language-Action Model |
| World Model Type | Web-knowledge transfer model for robotics |
| Primary Domain | Robotics |
| Architecture | PaLI-X / PaLM-E backbone fine-tuned with action tokenization |
| Modality | Visual + Language + Proprioceptive |
| Training Method | Co-fine-tuning on web VLM data + robot demonstration trajectories |
| Status | active |
| Year | 2023 |
| Performance Index | 72/100 (medium confidence, v1.1) |

## About RT-2

Main editorial body preserved directly in static HTML.

RT-2 (Robotic Transformer 2) is a vision-language-action (VLA) model that co-fine-tunes a large vision-language model on both web data and robotic trajectories. By tokenizing robot actions as text tokens, RT-2 enables a single model to perform visual question answering, image captioning, and robot control simultaneously. It demonstrates emergent capabilities such as reasoning about previously unseen objects, interpreting abstract instructions, and performing multi-step manipulation tasks, all without task-specific training.

RT-2 is a web-knowledge transfer model for robotics developed by Google DeepMind in 2023 for robotics.

## Editorial Snapshot

Short extractable facts for answer engines and no-JS readers.

| Signal | Value |
| --- | --- |
| Definition | RT-2 is a web-knowledge transfer model for robotics developed by Google DeepMind in 2023 for robotics. |
| Short Description | A vision-language-action model that transfers web-scale knowledge directly to robot control. |
| Benchmark Rows | 2 |
| FAQ Entries | 2 |
| Related Models | 4 |
| Related Guides | 0 |
| Related Research Topics | 1 |
| Last Updated | 2026-04-07 |

## Notable Features

Key capabilities associated with this model.

- • Emergent reasoning about novel objects
- • Action tokenization within language model
- • Zero-shot generalization to unseen instructions
- • Combines web knowledge with physical grounding

## Use Cases

Representative applications attached to this model record.

Robotic manipulation

Instruction-following robots

Object reasoning

Multi-step task execution

## Strengths and Limitations

Balanced assessment surfaced in static HTML.

### Strengths

- • Web-scale knowledge transfer
- • No task-specific modules needed
- • Handles novel objects and instructions
- • Unified architecture for perception and action

### Limitations

- • Requires large-scale compute
- • Limited to manipulation tasks in evaluation
- • Single-robot arm setting
- • Inference latency for real-time control

## Benchmarks

Published benchmark evidence attached to this model record.

| Benchmark | Metric | Result | Source |
| --- | --- | --- | --- |
| Emergent Skills Eval | Success Rate 62 % | 62% success on novel objects | [Source](https://arxiv.org/abs/2307.15818) |
| Language Table | Task Success 90 % | 90% success | [Source](https://arxiv.org/abs/2307.15818) |

## References and Citations

Primary references preserved in static HTML for citation extraction.

| Reference | Link |
| --- | --- |
| Brohan et al., 2023. RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control. arXiv:2307.15818 | [Open source](https://arxiv.org/abs/2307.15818) |

## Related Models

Nearby models linked from the current editorial record.

| Model | Category | World Model Type | Index v1.1 |
| --- | --- | --- | --- |
| [3D-VLA](https://world-models.io/en/models/3d-vla/) | Foundation World Model | 3D-aware embodied world model | 47/100 |
| [AMI World Model](https://world-models.io/en/models/ami-world-model/) | Foundation World Model | Announced multimodal world model initiative | N/A |
| [TD-MPC2](https://world-models.io/en/models/td-mpc2/) | Model-Based RL | Implicit dynamics + MPC planner | 80/100 |

## Direct Comparisons

Side-by-side comparisons already connected to this model.

| Comparison | Matchup | Summary |
| --- | --- | --- |
| [RT-2 vs 3D-VLA](https://world-models.io/en/compare/rt-2-vs-3d-vla/) | RT-2 vs 3D-VLA | Two approaches to vision-language-action models for robotics. RT-2 leverages web-scale VLM knowledge through action tokenization, while 3D-VLA integrates explicit 3D spatial understanding for embodied reasoning. |

## Research Topics Referencing This Model

Connected research areas surfaced directly in static HTML.

| Topic | Summary |
| --- | --- |
| [Language-Conditioned World Models](https://world-models.io/en/research/language-conditioned-world-models/) | How language-conditioned world models use text prompts or natural-language actions to control simulation, planning, and embodied behavior across Pandora, 3D-VLA, RT-2, and hybrid systems. |

## Frequently Asked Questions

FAQ answers rendered directly into static HTML for extractable responses.

### How does RT-2 differ from RT-1?

RT-1 was trained only on robot data. RT-2 co-fine-tunes a large vision-language model (PaLI-X or PaLM-E) on both web and robot data, enabling emergent reasoning capabilities that RT-1 lacks.

### Can RT-2 handle objects it has never seen?

Yes. By leveraging web-scale visual knowledge, RT-2 can reason about and manipulate objects not present in its robot training data, a key emergent capability.

## Quick Answer

Short extractable summary preserved directly in static HTML.

- RT-2 is a web-knowledge transfer model for robotics developed by Google DeepMind in 2023 for robotics.
- Use this page when you need a fast read on how RT-2 fits into the foundation world model landscape, then validate the details in the benchmarks, citations, and related pages.
- A key strength surfaced in the editorial record is web-scale knowledge transfer.

## Editorial Trust Signals

Editorial provenance and refresh policy preserved directly in static HTML.

**Published by** world-models.io editorial board.

**Lead editor** Tyler D. - Technical editor, methodology and benchmark analysis.

This model page synthesizes primary papers, official model pages, benchmark evidence, and related world-models.io context into a reference resource.

Each editorial page is assembled from primary sources, normalized into extractable summaries, checked for factual drift, and reviewed before publication or major refreshes. Last reviewed: 2026-04-07.

Pages are refreshed when a new paper, benchmark, release, architecture update, or stronger primary source materially changes the answer a reader or AI system should retrieve.

Each page links back to relevant primary sources and keeps a stable canonical URL so readers can verify claims, trace context, and reference the most up-to-date version. [See the editorial policy.](https://world-models.io/en/editorial-policy/)

Primary sources only

Last reviewed date visible

Methodology documented

Source links included

Correction channel published

Review date visible

## External Sources

Primary model and lab sources embedded in static HTML.

- [RT-2 paper](https://arxiv.org/abs/2307.15818) Google DeepMind primary research source
- [RT-2 official page](https://robotics-transformer2.github.io/) Google DeepMind official page
- [Google DeepMind official website](https://deepmind.google) Related lab

## References

1. [[1] Brohan et al., 2023. RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control. arXiv:2307.15818](https://arxiv.org/abs/2307.15818)