Swipe for more top models
Compare
Veo 3.1 vs Veo 3
Veo 3 edges out Veo 3.1 overall (Veo 3.1 56.0 vs Veo 3 60.0.) Veo 3 is an incredible model that proves Google is leading the pack in cinematic generations. It's great for cinematography and has built-in audio capability. It can struggle with logical worldbuilding on more creative camera requests, but most of the time it does quite well. Where it takes a step back: actor performances weren't as good as Veo 2, and the output has a glossier look. Veo 2 had more cinematic taste. Image-to-video tasks also struggle more than prior models. The main tradeoffs are in Actor performances, Logical worldbuilding, Has a glossy aesthetic, Image-to-video tasks, where Veo 3.1 tends to score better.
Veo 3.1Google | Veo 3Google |
|---|---|
Good for
| Good for
|
Bad for
| Bad for
|
Modalities
| Capability | Veo 3.1 | Veo 3 |
|---|---|---|
| Text input | ||
| Image input | ||
| Video input | ||
| Audio input | — | — |
| Image output | ||
| Audio output | — |
Providers
Provider
Google
google-veo
Google is the platform that serves Veo 3.1 requests, pricing, and availability.
Provider
Google
google-veo
Google is the platform that serves Veo 3 requests, pricing, and availability.
Physics
How well the model simulates real-world physics: gravity, momentum, collisions, and natural movement.
Veo 3 leads on physics (+2.3), with a measurable advantage over Veo 3.1. The clearest separation is on Physics (+2.3). Across the other sub-metrics in this group, the gap is smaller but generally consistent with the overall direction. If physics is a priority for your prompts, Veo 3 is the safer pick here.
| Metric | Veo 3.1 | Veo 3 |
|---|---|---|
| Physics | 55.9 | 58.2 |
Prompt and Logic
Measures how accurately the model follows prompts and maintains logical consistency throughout the video.
Veo 3 leads on prompt and logic (+4.4), with a measurable advantage over Veo 3.1. The clearest separation is on Scene Consistency (+20.1). 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 is the safer pick here.
| Metric | Veo 3.1 | Veo 3 |
|---|---|---|
| Prompt Adherence | 67.0 | 54.0 |
| Logic Consistency | 47.2 | 53.2 |
| Scene Consistency | 50.6 | 70.7 |
Aesthetics
Visual quality including cinematography, artistic taste, and overall production value.
Veo 3 leads on aesthetics (+4.3), with a measurable advantage over Veo 3.1. The clearest separation is on Cinematography (+8.5). 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 3 is the safer pick here.
| Metric | Veo 3.1 | Veo 3 |
|---|---|---|
| Cinematography | 47.3 | 55.9 |
| Taste | — | — |
| Quality | 0.6 | 0.7 |
Animation
Performance on animated content styles including 2D, 3D, and anime-style animation.
Veo 3 leads on animation (+6.1), with a measurable advantage over Veo 3.1. The clearest separation is on 3D Animation (+10.0). 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 is the safer pick here.
| Metric | Veo 3.1 | Veo 3 |
|---|---|---|
| 2D Animation | 46.0 | 53.0 |
| 3D Animation | 54.0 | 64.0 |
| Anime Animation | 48.3 | 49.7 |
Humans
Accuracy of human rendering including body proportions, hand details, and realistic actor performances.
Veo 3.1 leads on humans (+9.5), with a measurable advantage over Veo 3. The clearest separation is on Hands (+26.3). Across the other sub-metrics in this group, the gap is smaller but generally consistent with the overall direction. If humans is a priority for your prompts, Veo 3.1 is the safer pick here.
| Metric | Veo 3.1 | Veo 3 |
|---|---|---|
| Human | 61.9 | 54.7 |
| Hands | 76.3 | 50.0 |
| Actor Performance | 40.0 | 45.0 |
Objects and Animals
Quality of rendering inanimate objects and animals with accurate shapes, textures, and movements.
Veo 3.1 and Veo 3 are effectively tied on objects and animals, with small tradeoffs across the metrics. The biggest separation is on Objects (6.0), 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.
| Metric | Veo 3.1 | Veo 3 |
|---|---|---|
| Objects | 61.7 | 67.6 |
| Animals | 68.0 | 63.3 |
Text
Ability to render readable, accurate text and typography within generated videos.
Veo 3 leads on text (+3.2), with a measurable advantage over Veo 3.1. The clearest separation is on Text Fidelity (+3.2). 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 3 is the safer pick here.
| Metric | Veo 3.1 | Veo 3 |
|---|---|---|
| Text Fidelity | 39.5 | 42.7 |
Cost and Speed
Practical factors including pricing per video and generation latency.
Veo 3 leads on cost and speed (+28.3), 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 3 is the safer pick here.
| Metric | Veo 3.1 | Veo 3 |
|---|---|---|
| Price / sec | $0.200 | $0.200 |
| Price / min | $12.00 | $12.00 |
| Latency | 935ms | 850ms |