multimodal LLM
Gemini Robotics-ER 2
Embodied reasoning model in public preview in AI Studio and the Gemini API.
Levelmodel
Classmultimodal LLM
Parametersnot in the notes
Contextnot in the notes
Released30 Jul 2026
Opennessproprietary
Runs onnot in the notes
Statuspreview
Benchmark Results
vendor-reported
Gemini Robotics 2 vendor task evaluationsworld models and robotics
Moment findingvendor-reported
91.3
050100
Score in %. Higher is better.
Vendor, Jul 2026 (via aiwiki)
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Lineage
successorfinetune
Gemini 3.5 Flash is the parent (finetune)medium confidencepress claimGemini Robotics-ER 1.6 is the parent (successor)low confidencenotesWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 5 models. Confidence and evidence are the notes' own.
Identity
- Developer
- Google DeepMind
- Family
- Gemini Robotics 2
- Released
- 30 Jul 2026 sourcessecondary report
- Weights published
- –
- Record checked
- 10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- not in the notes Orchestrates the VLA as a tool with bidirectional streaming; built on Gemini 3.5 Flash
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- image, video, text
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- proprietary
- Licence
- Proprietary sources
- Access routes
- API
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Industry Use Cases
No industry use case links this model.
Links
ModelGemini Robotics-ER 2Google DeepMind, multimodal LLM
Gemini Robotics-ER 2Google DeepMind, multimodal LLMUse CasesRobot Inspection with Instrument ReadingIndustrialUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs Itnone recordedDeployments of these use cases; none names this model.
Models 3
Organisations 1
Sources
- aiwiki.ai/wiki/gemini_robotics_2 https://aiwiki.ai/wiki/gemini_robotics_2
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Gemini Robotics-ER 2", https://aurion.semai.id/models/google-deepmind-gemini-robotics-er-2/, records of October 2026.