Futurepedia | Veo 3.1 is Here | Full Test vs Sora 2 Pro and Wan 2.5

My Account

Mijn Account

Mon Compte

Mein Konto

我的帐户

Connexion

Anmeldung

Futurepedia | Veo 3.1 is Here | Full Test vs Sora 2 Pro and Wan 2.5

I tested the three newest AI video models released in 2025: Veo 3.1, Sora 2 Pro, and Wan 2.5. Here's my complete breakdown of which model is best at what.

I test multiple categories including physics simulation, camera movement, emotional expression, dialogue, action scenes, stylistic range, and more.

Veo 3.1 just dropped with major upgrades. Sora 2 took over the app store. But Wan 2.5 has been flying under the radar despite having comparable capabilities in complex physics and audio generation.

After extensive testing, I break down exactly which model excels in different scenarios and which one you should use depending on your needs.

Where to use Veo 3.1

https://higgsfield.ai

https://fal.ai/models/fal-ai/veo3.1

https://replicate.com/google/veo-3.1

https://wavespeed.ai/models/google/veo3.1/text-to-video

https://huggingface.co/spaces/akhaliq/veo3.1-fast

Where to use Sora 2

https://openart.ai/video/i2v/sora-v2

Where to use Wan 2.2

https://wan2-2.org/wan2-2

Where to use Wan 2.5

https://www.wan-ai.co/wan-2-5

Where to use Kling

https://app.klingai.com/global/image-to-video/frame-mode/new

Where to use Hailuoai 2

https://hailuoai.video

Where to use Flow

https://labs.google/fx/tools/flow

00:00 - Intro

00:33 - The domino challenge

02:14 - Basketball physics

03:23 - Alarm challenge

04:27 - Dialogue challenges

07:30 - Singing and music

10:00 - Creating dialogue

12:40 - Specific dialogue

13:55 - Non-human dialogue

15:16 - Veo 3.1 start and end frame

17:50 - Veo 3.1 ingredients

18:43 - Wan camera controls

19:15 - Sora 2 sketch to video

21:14 - Laughing

22:15 - Crying

23:14 - Title screen

23:52 - Writing cursive

24:29 - Unique camera shots

25:40 - Stylistic range

28:01 - Physics and complex movements

31:04 - The winner is...

33:34 - Weirdest generation

33:56 - Futurepedia

AI News

technology and ai

Futurepedia | Veo 3.1 is Here | Full Test vs Sora 2 Pro and Wan 2.5

Join the conversation 🎭

GLM 5.2 | The New King | Best Open Source AI Model

A Fable’s End: 11 Things You Missed as Claude Nixed

AI Revolution | The Internet is No Longer Human

AI Buys Robot and Car, Does Exactly What Experts Warned

RIP Claude Fable | Full Body Avatars | New Google Models

Greg Isenberg | Claude Fable 5 is Banned, What to do?

Matthew Berman | Claude Mythos Just got Banned!

Visual Venture | The Darkest A.I. Conversations Ever Recorded

Sabine | It's Happening: AI is Starting to Improve Itself

BBC News | Is this AI's Moment of Truth?

Matt Wolfe | An Insane AI Week... Here’s What Matters

Anthropic Begged the World to stop AI… then shipped this

AI Search | Claude Fable 5 is here!

TechLinked | Buckle Up, Windows Users

Matt Wolfe | The Truth About Anthropic's Mythos

The Dark Side of AI | Exploitation of Humans and Nature

The Circuit | Inside Anthropic: The $965 Billion AI Juggernaut

Anthropic Claude Fable 5 | First Publicly Available Mythos-Class AI Model

MattVidPro AI | Hands on: Fable 5 Makes GPT 5.5 Feel Like a Toy

Infographics | The $15,000 AI Bill. Your $20 Subscription is a Delusion

Fireship | Anthropic is Starting to Panic…

The AI Take Over Has Completely Backfired and I Can't Be Happier

Ideogram | Best Local AI Image Generator is Here!

Apple WWDC Impressions | Siri AI is... Interesting.

Four Corners | The AI Takeover: Who Controls Our Future?

Bloomberg | Why an AI 'Death Spiral' Threatens the Internet

Dr. Brian Keating | Terence Tao Explains The Math Behind AI

Dan Dingle | Google Street View is Now Playable AI Slop

Matt Wolfe | Microsoft Finally Reveals They're Plan!

Why I Quietly Switched From Codex to Claude Code