<report>

Google

Veo 3.1

v-benchmark v2 by Megaton benchmark
Generated via Google · July 27, 2026Evaluated · August 9, 2026Leaderboard rank #13 of 15Last updated · September 10, 2026

62.41

/ 100

Affiliate link: Megaton may earn a commission if you purchase, at no extra cost to you.

Get the latest video releases and leaderboard updates

Categories

C01

Prompt AdherenceWhether every explicit, observable instruction in the prompt is fulfilled.

This Video

95.5

This Video · Assessment

This video fulfills its explicit, observable instructions with near-complete consistency.

This Category

79.5

36 videos were rated for this category

This Category · Assessment

Most prompt requirements are fulfilled, though complex combinations or secondary details recur as limitations.

Models that scored similarly on this category

Violations

This Video
Essential0
Major1
Minor0
This Category
Essential25
Major21
Minor15

36 videos

C02

Scene ConsistencyWhether established subjects, objects, spatial relationships, environment, and lighting remain coherent over time.

This Video

40.0

This Video · Assessment

This video maintains subjects, objects, spatial relationships, environment, and lighting over time only partly reliably, with frequent important failures.

This Category

80.0

36 videos were rated for this category

This Category · Assessment

Temporal and spatial continuity is highly reliable, with only isolated drift or regeneration.

Models that scored similarly on this category

Violations

This Video
Essential2
Major0
Minor0
This Category
Essential28
Major20
Minor9

36 videos

C03

PhysicsWhether the central motion, force, material, and reaction behave coherently in the requested world and style.

This Video

40.0

This Video · Assessment

The event occurs, but its physical behavior is clearly implausible.

This Category

45.3

17 videos were rated for this category

This Category · Assessment

Physics is only partly reliable; implausible trajectories, contacts, or material behavior recur frequently.

Models that scored similarly on this category

C04

Human FidelityWhether faces, eyes, skin, bodies, hands, motion, and human presence remain anatomically and perceptually convincing.

This Video

90.0

This Video · Assessment

Highly convincing, with one very small localized defect.

This Category

65.9

27 videos were rated for this category

This Category · Assessment

People remain believable in most cases, though uncanny or anatomical defects recur under inspection.

Models that scored similarly on this category

C05

2D Animation Craft & ArtistryThe quality and artistic authorship of intentionally 2D animation within its requested conventions.

This Video

30.0

This Video · Assessment

Severe morphing, timing, drawing, or medium-authenticity failures.

This Category

45.0

12 videos were rated for this category

This Category · Assessment

Coherent 2D craft appears only in some cases; line, timing, pose, or medium-authenticity failures recur frequently.

Models that scored similarly on this category

C06

3D Animation Craft & ArtistryThe quality, coherence, and artistic authorship of intentionally 3D animation.

This Video

30.0

This Video · Assessment

Severe deformation, articulation, contact, rendering, or medium-coherence failures.

This Category

49.0

5 videos were rated for this category

This Category · Assessment

Convincing 3D craft appears only in some cases; articulation, contact, rendering, or staging failures recur frequently.

Models that scored similarly on this category

C07

Cinematography Craft & ArtistryShot design, framing, camera movement, lighting, focus, visual hierarchy, and intentional filmmaking authorship.

This Video

60.0

This Video · Assessment

Coherent and competent but synthetic, mechanical, or visually underdeveloped.

This Category

62.9

7 videos were rated for this category

This Category · Assessment

Cinematography is generally coherent and capable, but mechanical or underdeveloped visual choices recur.

Models that scored similarly on this category

C08

Taste & Art DirectionThe strength, specificity, coherence, and artistic authorship of the result as a finished creative choice.

This Video

60.0

This Video · Assessment

Competent but visibly reliant on familiar AI aesthetics or underdeveloped art direction.

This Category

51.9

60 videos were rated for this category

This Category · Assessment

Successful choices are mixed with repeated inconsistency or familiar AI aesthetics.

Models that scored similarly on this category

C09

Animal & Creature FidelityWhether real animals and designed creatures preserve convincing anatomy, identity, motion, behavior, and interaction.

This Video

60.0

This Video · Assessment

Coherent but noticeably synthetic, anatomically strained, or behaviorally unnatural.

This Category

67.1

7 videos were rated for this category

This Category · Assessment

Animals and creatures remain believable in most cases, though synthetic anatomy, motion, or behavior recurs.

Models that scored similarly on this category

C10

Object & Product FidelityWhether requested objects have correct identity, structure, materials, details, motion, and interactions.

This Video

100.0

This Video · Assessment

This video preserves the requested objects’ identity, structure, materials, details, motion, and interactions with near-complete consistency.

This Category

95.4

8 videos were rated for this category

This Category · Assessment

Requested objects preserve identity, structure, materials, details, motion, and interactions with near-complete consistency.

Violations

This Video
Essential0
Major0
Minor0
This Category
Essential3
Major4
Minor0

8 videos

C11

Causal & Semantic CoherenceWhether events, relationships, transformations, and cause-and-effect remain semantically coherent, including surreal premises.

This Video

80.0

This Video · Assessment

Clear overall, with a few non-disruptive logical irregularities.

This Category

65.5

11 videos were rated for this category

This Category · Assessment

Central events are generally understandable, but strained or unexplained actions and relationships recur.

Models that scored similarly on this category

C12

Text FidelityWhether requested text content, typography, placement, attachment, legibility, and temporal stability are correct.

This Video

61.1

This Video · Assessment

This video preserves requested text content, typography, placement, attachment, legibility, and temporal stability in a generally coherent way, though visible failures recur.

This Category

41.7

6 videos were rated for this category

This Category · Assessment

Only some text is rendered reliably; spelling, legibility, placement, or temporal failures are frequent.

Models that scored similarly on this category

Violations

This Video
Essential4
Major0
Minor0
This Category
Essential26
Major8
Minor1

6 videos

C13

Character Performance & ActingWhether character intention, emotion, timing, reactions, eyelines, gesture, and performance read convincingly.

This Video

60.0

This Video · Assessment

Readable but synthetic, generalized, or mechanically delivered.

This Category

62.0

21 videos were rated for this category

This Category · Assessment

Acting is generally believable, but synthetic timing, expression, attention, or specificity recurs.

Models that scored similarly on this category

Differences between other models

Megatonmegaton.ai

C01Prompt Adherence

Veo 3.1Kling 3 StandardSeedance 2.0 MiniGen-4.5LTX 2.3 22B
Megatonmegaton.ai

C03Physics

Veo 3.1Kling 3 StandardSeedance 2.0 MiniGen-4.5LTX 2.3 22B
Megatonmegaton.ai

C02Scene Consistency

Veo 3.1Kling 3 StandardSeedance 2.0 MiniGen-4.5LTX 2.3 22B
Megatonmegaton.ai

C04Human Fidelity

Veo 3.1Kling 3 StandardSeedance 2.0 MiniGen-4.5LTX 2.3 22B
Megatonmegaton.ai

C052D Animation Craft & Artistry

Veo 3.1Kling 3 StandardSeedance 2.0 MiniGen-4.5LTX 2.3 22B
Megatonmegaton.ai

C063D Animation Craft & Artistry

Veo 3.1Kling 3 StandardSeedance 2.0 MiniGen-4.5LTX 2.3 22B
Megatonmegaton.ai

C11Causal & Semantic Coherence

Veo 3.1Kling 3 StandardSeedance 2.0 MiniGen-4.5LTX 2.3 22B
Megatonmegaton.ai

C08Taste & Art Direction

Veo 3.1Kling 3 StandardSeedance 2.0 MiniGen-4.5LTX 2.3 22B
Megatonmegaton.ai

C07Cinematography Craft & Artistry

Veo 3.1Kling 3 StandardSeedance 2.0 MiniGen-4.5LTX 2.3 22B
Megatonmegaton.ai

C09Animal & Creature Fidelity

Veo 3.1Kling 3 StandardSeedance 2.0 MiniGen-4.5LTX 2.3 22B
Megatonmegaton.ai

C10Object & Product Fidelity

Veo 3.1Kling 3 StandardSeedance 2.0 MiniGen-4.5LTX 2.3 22B
Megatonmegaton.ai

C12Text Fidelity

Veo 3.1Kling 3 StandardSeedance 2.0 MiniGen-4.5LTX 2.3 22B
Megatonmegaton.ai

C13Character Performance & Acting

Veo 3.1Kling 3 StandardSeedance 2.0 MiniGen-4.5LTX 2.3 22B
CategoryVeo 3.1Kling 3 StandardSeedance 2.0 MiniGen-4.5LTX 2.3 22B
C01Prompt Adherence79.582.687.776.173.0
C03Physics45.357.650.638.840.0
C02Scene Consistency80.082.578.078.164.2
C04Human Fidelity65.979.664.867.450.7
C052D Animation Craft & Artistry45.046.461.747.533.3
C063D Animation Craft & Artistry49.066.062.044.042.5
C11Causal & Semantic Coherence65.566.470.972.746.4
C08Taste & Art Direction51.963.160.749.742.0
C07Cinematography Craft & Artistry62.975.767.170.058.6
C09Animal & Creature Fidelity67.171.482.961.444.3
C10Object & Product Fidelity95.490.088.474.548.3
C12Text Fidelity41.730.363.847.211.6
C13Character Performance & Acting62.059.063.063.041.0

Leaderboard

Megatonmegaton.ai
Megaton

Video Index

Measuring video model quality and performance

Video Index · 0–100

Scores are from the active Megaton v-benchmark v2.0 publication. See how our scores are calculated in our Methodology.

<Cite this report>

Citation snippet

Copy a plain-text citation for articles and research.

Megaton. “Veo 3.1 V-Benchmark v2 report.” V-Benchmark results publication 1.4.0, September 10, 2026. https://megaton.ai/evaluations/google/veo_3_1/report

Report badge

The badge links to this report so readers can verify the ranking.

Veo 3.1 is ranked #13 in Megaton V-Benchmark v2

Methodology

Our score is based on our v-benchmark v2 methodology.

Read the full methodology →

Changelog

Published
August 11, 2026
V-Benchmark version
2.1.0
Megaton Index
62.41
Published rank
13 of 15
View model changelog →

<What you get>

  • The prompts and outputs used in our tests.
  • Scores and notes explaining each result.
  • Comparisons with other models and versions.

<Who can get access>

  • Are you part of the Google team? Please reach out for complimentary access.
  • University and nonprofit researchers can ask about research access.
  • Paid access starts at $2,500 per report.
Access option

We’ll use these details to reply to your request.