Google DeepMind · Veo

Veo 2

READER SUMMARY

Google's second-generation video model with improved physical realism, cinematography understanding, output up to 4K and initial access through VideoFX.

DOOM SCORE51.8out of 100model risk profile, not the overall index

CURRENT ASSESSMENT · REVISION 1

Why this model scores 51.8

Veo 2 substantially advances realistic and controllable video generation but is not an independent agent. Waitlisted Labs access keeps deployment low at release, while SynthID and hosted controls reduce control difficulty despite substantial synthetic-media misuse potential.

Capability69

Autonomy6

Deployment30

Misuse potential65

Control difficulty45

0 comments · 0 votesOpen discussion

No comments yet. Start the discussion.

MODEL-ATTRIBUTED EVIDENCE

News tied to Veo 2

The model score of 51.8 rates this model's risk profile. The overall Doom Index of 63.2 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.03

Each article's leave-one-out Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores are recalculated from their technical profile and related news, but never feed back into the overall index.

16 Dec 2024CapabilityTOWARD

Google releases Veo 2 through VideoFX

Google introduced Veo 2 with improved physical realism, cinematography control and output up to 4K, while expanding access through its VideoFX experimental deployment.

Full item contribution: +0.03
Veo 2 equal share: +0.03

Read assessment →

AUDIT TRAIL

Model score history

R1
Doom Score 51.8
Initial exact source-backed profile for the Veo 2 release.
12 Aug 2026