Skip to main content

Google DeepMindVideo modelResearch preview for trusted testers

Genie 4

Summary

Google DeepMind describes Genie 4 as an interactive world model that generates video, ambient sound, music, and dialogue together. The announcement is dated October 27, 2026 and says the research preview is for trusted testers. It does not document public API access, pricing, or numeric benchmarks.

The announcement identifies drift and physical, spatial, language, and temporal consistency as open research questions. The official model-card directory has no dedicated Genie 4 card.

All specifications

Input and output

Capabilities
Real-time interactive world simulation with video, ambient sound, music, dialogue, and character motion
Source: Capabilities
Modality details
Interactive video with generated music, ambient sound, and dialogue
Source: Modality details

Licence and access

Announcement
Announced on October 27, 2026; no release date stated
Source: Announcement
Access
Research preview for trusted testers; no public API availability established
Source: Access

Further details

Model card
The official DeepMind model-card directory does not list a dedicated Genie 4 model card.
Source: Model card
Stated limitations
Google identifies ongoing work on drift and on physical, spatial, language, and temporal consistency.
Source: Stated limitations
Announcement
Oct 27, 2026
Source: Announcement
Research preview
Trusted testers only
Source: Research preview
Known limitations
Drift and consistency remain areas of active work
Source: Known limitations

Sources and data date

TypeEvidence and data date
Research statusResearch date October 29, 2026. 58 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not found in the inspected sources

Genie 4 model card

Note

The official model-card directory has no dedicated Genie 4 card.

Not published

Numeric benchmark results

Note

The official announcement gives no numeric Genie 4 benchmark results. No Genie 3 or other model scores are attributed to Genie 4.

Not published

Public API, pricing, and general availability

Note

The reviewed source describes a trusted-tester research preview and future availability plans, not public API access or current pricing.

Not found in the inspected sources

Vals rows in captured payloads

Note

Nine complete Vals payloads dated 28 October were checked; no exact model ID or unambiguous model label. Limited to these saved benchmarks.

Unresolved

Uncaptured Arena Code/Speech leaderboards

Note

Text, Agent including Code/Chat/Work, and twelve WebDev views were captured. A separate general Code and Arena Speech leaderboard were not saved as complete tables.

Unresolved

Artificial Analysis catalog reconciliation

Note

The full current AA model and benchmark catalog was not re-reconciled for this profile in this sidecar. This sidecar makes no AA absence claim; native AA imports remain authoritative.

Additional sourceGoogle DeepMind Genie 4 announcement (retrieved October 29, 2026) · Google DeepMind Genie 4 announcement · Editorial description reviewed October 29, 2026
Additional sourceGoogle DeepMind model-card directory (retrieved October 29, 2026) · Google DeepMind model-card directory · Editorial description reviewed October 29, 2026
Additional sourceModel metadata (retrieved October 29, 2026)12