Compare

Veo 3.1 vs Veo 2

These two models are effectively tied overall (Veo 3.1 56.0 vs Veo 2 56.0.)

Google
Google
Veo 3.1
56
56
Total Score
Veo 3.1
View
rank
#6
cost
12.00
/min
speed
935
ms
Google
Google
Veo 2
56
56
Total Score
Veo 2
View
rank
#6
cost
30.00
/min
speed
850
ms
Veo 3.1Google
Veo 2Google
Good for
  • Animation
  • Prompt and Logic
Good for
  • Cost and Speed
  • Text
  • Aesthetics
  • Objects and Animals
Bad for
  • Cost and Speed
  • Text
  • Aesthetics
Bad for
  • Animation
  • Prompt and Logic
Modalities
CapabilityVeo 3.1Veo 2
Text input
Image input
Video input
Audio input
Image output
Audio output

Providers

Google
Provider
Google
google-veo
Google is the platform that serves Veo 3.1 requests, pricing, and availability.
Google
Provider
Google
google-veo
Google is the platform that serves Veo 2 requests, pricing, and availability.

Physics

Veo 3.1 and Veo 2 are effectively tied on physics, with small tradeoffs across the metrics. The biggest separation is on Physics (0.3), but it's not decisive overall. In practice, you should decide based on the specific sub-metric you care about most, since neither model consistently dominates this slice of the rubric.
MetricVeo 3.1Veo 2
Physics55.956.2

Prompt and Logic

Veo 3.1 leads on prompt and logic (+3.6), with a measurable advantage over Veo 2. The clearest separation is on Prompt Adherence (+9.0). Across the other sub-metrics in this group, the gap is smaller but generally consistent with the overall direction. If prompt and logic is a priority for your prompts, Veo 3.1 is the safer pick here.
MetricVeo 3.1Veo 2
Prompt Adherence67.058.0
Logic Consistency47.238.3
Scene Consistency50.657.7

Aesthetics

Veo 2 leads on aesthetics (+10.2), with a measurable advantage over Veo 3.1. The clearest separation is on Cinematography (+20.4). Across the other sub-metrics in this group, the gap is smaller but generally consistent with the overall direction. If aesthetics is a priority for your prompts, Veo 2 is the safer pick here.
MetricVeo 3.1Veo 2
Cinematography47.367.7
Taste
Quality0.60.6

Animation

Veo 3.1 leads on animation (+14.5), with a measurable advantage over Veo 2. The clearest separation is on 2D Animation (+23.0). Across the other sub-metrics in this group, the gap is smaller but generally consistent with the overall direction. If animation is a priority for your prompts, Veo 3.1 is the safer pick here.
MetricVeo 3.1Veo 2
2D Animation46.023.0
3D Animation54.054.5
Anime Animation48.327.3

Humans

Veo 3.1 and Veo 2 are effectively tied on humans, with small tradeoffs across the metrics. The biggest separation is on Actor Performance (25.3), but it's not decisive overall. In practice, you should decide based on the specific sub-metric you care about most, since neither model consistently dominates this slice of the rubric.
MetricVeo 3.1Veo 2
Human61.952.7
Hands76.359.9
Actor Performance40.065.3

Objects and Animals

Veo 2 leads on objects and animals (+1.9), with a measurable advantage over Veo 3.1. The clearest separation is on Animals (+7.8). Across the other sub-metrics in this group, the gap is smaller but generally consistent with the overall direction. If objects and animals is a priority for your prompts, Veo 2 is the safer pick here.
MetricVeo 3.1Veo 2
Objects61.757.8
Animals68.075.8

Text

Veo 2 leads on text (+14.5), with a measurable advantage over Veo 3.1. The clearest separation is on Text Fidelity (+14.5). Across the other sub-metrics in this group, the gap is smaller but generally consistent with the overall direction. If text is a priority for your prompts, Veo 2 is the safer pick here.
MetricVeo 3.1Veo 2
Text Fidelity39.554.0

Cost and Speed

Veo 2 leads on cost and speed (+22.2), with a measurable advantage over Veo 3.1. The clearest separation is on Latency (+85.0). Across the other sub-metrics in this group, the gap is smaller but generally consistent with the overall direction. If cost and speed is a priority for your prompts, Veo 2 is the safer pick here.
MetricVeo 3.1Veo 2
Price / sec$0.200$0.500
Price / min$12.00$30.00
Latency935ms850ms