Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Today we’re launching OpenArt Arena, the global leaderboard for creative intelligence. Every AI model claims to be the best. But best at what? We brought together creative professionals to evaluate the world’s leading AI models blindly, across the work creators actually care about: Film. Ads. Animation. Motion design. Video... show more

OpenArt

78,984 subscribers

5,123,764 Aufrufe • vor 7 Tagen •via X (Twitter)

Kunst Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

22 Kommentare

Profilbild von OpenArt

OpenArtvor 7 Tagen

The first rankings are live →

Profilbild von MayorkingAI

MayorkingAIvor 7 Tagen

This makes a lot more sense. I use different models for different things all the time character design, animation, motion, video... There’s really no “best model” anymore. It all depends on what you’re trying to create

Profilbild von safalexeai

safalexeaivor 7 Tagen

I work on OpenArt and I follow it so I know it will have better and True Leadership and not like what @arena has, Fake Hyped and Paid. Good Luck OpenArt

Profilbild von AmirMušić

AmirMušićvor 7 Tagen

Love this! First exploration 👀

Profilbild von Polash Khan

Polash Khanvor 7 Tagen

This is fantastic! It's so important to have real creators weigh in on AI model performance. Looking forward to seeing the resul

Profilbild von Hafiz Siddiq

Hafiz Siddiqvor 7 Tagen

The useful cut is whether the leaderboard predicts durable creative outcomes, not just taste on a benchmark. Which signal separates novelty from work people actually keep using?

Profilbild von Rafa Gonzalez | IA

Rafa Gonzalez | IAvor 7 Tagen

Estupendo !!!

Profilbild von PromptSin

PromptSinvor 7 Tagen

Thank you for creating this model comparison tool, where we, the users, decided which one is the best in each category.

Profilbild von Mehwish kiran

Mehwish kiranvor 7 Tagen

Finally, AI models judged by creators, not just benchmarks.

Profilbild von Amira Zairi

Amira Zairivor 7 Tagen

This is way more useful than another benchmark, I just want to know which model actually works best for what I’m creating

Profilbild von Aryan SMM

Aryan SMMvor 7 Tagen

blind testing also makes the results much easier to trust

Profilbild von Paul Young

Paul Youngvor 7 Tagen

La meilleure IA n'existe pas, il n'y a que la meilleure IA pour ce que vous voulez créer✨

Profilbild von Sidvexo Ai

Sidvexo Aivor 7 Tagen

Best thing out in market now 😎

Profilbild von Usman

Usmanvor 7 Tagen

Finally, AI models judged by creators, not just benchmarks.

Profilbild von Alex Rivas | IA

Alex Rivas | IAvor 7 Tagen

Increible lo que se pude hacer hoy

Profilbild von Easton Coleford | AI

Easton Coleford | AIvor 7 Tagen

Congrats !

Profilbild von Gabriel Santos | IA

Gabriel Santos | IAvor 7 Tagen

Muito forte !

Profilbild von Arina Ai

Arina Aivor 7 Tagen

Very well made.

Profilbild von Aaliya

Aaliyavor 7 Tagen

This makes comparing AI models much easier for creators.

Profilbild von Keitaro3660

Keitaro3660vor 7 Tagen

Nice, We can trust the result, because almost all the number 1 video gen rank are Seedance 2.5 😂 unlike those other 'ai arena platform'

Profilbild von Artists Voyage 🔶

Artists Voyage 🔶vor 7 Tagen

comparing models on real creative work is much more useful than chasing one overall ranking

Profilbild von Ezzaldeen

Ezzaldeenvor 7 Tagen

Amazing

Ähnliche Videos

Most people rank AI models like there's one winner. Every lab says their model is #1. OpenArt Arena hid the logos and had creative pros vote blind, then ranked by the actual job: > Film > Ads > Lip Sync > and more Global Leaderboard for Creative AI

Most people rank AI models like there's one winner. Every lab says their model is #1. OpenArt Arena hid the logos and had creative pros vote blind, then ranked by the actual job: > Film > Ads > Lip Sync > and more Global Leaderboard for Creative AI

Min Choi

402,082 Aufrufe • vor 6 Tagen

Intelligence cofounder Grace Li wants to build an intelligence marketplace for AI capabilities, not just a leaderboard that tells you which model is best. Today, Design Arena users submit creative tasks and have multiple AI models attempt it. The company then collects users' preference about which result was best, which gives Intelligence data about which models perform well for particular kinds of work. Grace thinks that in the future, it will become way easier for companies and individuals to customize models for one narrow purpose and sell access to it on a marketplace. She explains:

Intelligence cofounder Grace Li wants to build an intelligence marketplace for AI capabilities, not just a leaderboard that tells you which model is best. Today, Design Arena users submit creative tasks and have multiple AI models attempt it. The company then collects users' preference about which result was best, which gives Intelligence data about which models perform well for particular kinds of work. Grace thinks that in the future, it will become way easier for companies and individuals to customize models for one narrow purpose and sell access to it on a marketplace. She explains:

TBPN

99,788 Aufrufe • vor 1 Monat

There are hundreds of AI models, but no single model is best at everything. DGrid AI's AI Arena lets 300,000+ users blind-test model responses and vote for the better one, helping map which models perform best for different tasks.

There are hundreds of AI models, but no single model is best at everything. DGrid AI's AI Arena lets 300,000+ users blind-test model responses and vote for the better one, helping map which models perform best for different tasks.

Cointelegraph

64,223 Aufrufe • vor 2 Monaten

ELON: CHINA HAS THE BEST OPEN SOURCE AI MODELS RIGHT NOW “The best open source models are generally from China, which is bizarre. I think the second best one, or maybe it’s better than second best, is Grok 2.5. The open source model is actually very good, and we will continue to open source our models.” Source: The All-In Podcast

ELON: CHINA HAS THE BEST OPEN SOURCE AI MODELS RIGHT NOW “The best open source models are generally from China, which is bizarre. I think the second best one, or maybe it’s better than second best, is Grok 2.5. The open source model is actually very good, and we will continue to open source our models.” Source: The All-In Podcast

Mario Nawfal

1,163,582 Aufrufe • vor 10 Monaten

The OpenArtist Program is officially public. We spent months handpicking 120 of the world's best AI creators. Today, for the first time, we're opening the doors to everyone. • Get paid for every post • Early access to every model and feature we launch. • A community of the most creative AI artists in the world. • A real chance to join the OpenArt team. 150 spots total. 120 taken. 30 left. Apply before they're gone.

The OpenArtist Program is officially public. We spent months handpicking 120 of the world's best AI creators. Today, for the first time, we're opening the doors to everyone. • Get paid for every post • Early access to every model and feature we launch. • A community of the most creative AI artists in the world. • A real chance to join the OpenArt team. 150 spots total. 120 taken. 30 left. Apply before they're gone.

OpenArt

3,131,713 Aufrufe • vor 4 Monaten

Tired of guessing which AI model is best? 🤔 We've got you covered! 👀 Here's a sneak peek of our new model comparison feature in action! Run the same prompt across multiple models and see which one works best for YOU. Which models are you excited to test? #Inferium #AI #Inference #Compare

Tired of guessing which AI model is best? 🤔 We've got you covered! 👀 Here's a sneak peek of our new model comparison feature in action! Run the same prompt across multiple models and see which one works best for YOU. Which models are you excited to test? #Inferium #AI #Inference #Compare

Inferium

12,352 Aufrufe • vor 1 Jahr

GPT-6 Astra is by far the best 3D design model today. & this is THE Complete Tutorial Guide to Design in Codex. FULL guide you need to know about Codex and GPT-6 to start using it for design work and 3D creative work.

GPT-6 Astra is by far the best 3D design model today. & this is THE Complete Tutorial Guide to Design in Codex. FULL guide you need to know about Codex and GPT-6 to start using it for design work and 3D creative work.

Viktor Oddy

143,165 Aufrufe • vor 4 Tagen

AI has changed what I—and I think most people—are looking for in candidates today. It’s not about blindly using AI and following what it says; it’s about being an independent, creative, and critical thinker who knows how to partner well with AI to bring about the best total intelligence. I explore this topic and more in the new AI-powered Masterclass Executive online program, which I’ve joined as an instructor. The program is starting soon, and if you’re interested, you can apply here:

AI has changed what I—and I think most people—are looking for in candidates today. It’s not about blindly using AI and following what it says; it’s about being an independent, creative, and critical thinker who knows how to partner well with AI to bring about the best total intelligence. I explore this topic and more in the new AI-powered Masterclass Executive online program, which I’ve joined as an instructor. The program is starting soon, and if you’re interested, you can apply here:

Ray Dalio

128,156 Aufrufe • vor 4 Monaten

Before Allora, AI was model centric, forcing teams to chase and maintain the “right” model for every task. After Allora, Users set the goal and Allora Network coordinates thousands of models in real time for the best output. Allora Mainnet is the shift the age of intelligence needs.

Before Allora, AI was model centric, forcing teams to chase and maintain the “right” model for every task. After Allora, Users set the goal and Allora Network coordinates thousands of models in real time for the best output. Allora Mainnet is the shift the age of intelligence needs.

Allora

79,895 Aufrufe • vor 10 Monaten

China is the first nation to truly embrace and master AI video. They not only have the best AI video model (Seedance 2) but they also have some of the best AI creators in the world. Credit: viktro99 on IG

China is the first nation to truly embrace and master AI video. They not only have the best AI video model (Seedance 2) but they also have some of the best AI creators in the world. Credit: viktro99 on IG

Mark Gadala-Maria

52,431 Aufrufe • vor 3 Monaten

VEO 2 is here. Google DeepMind’s most advanced AI video model—now live on Nfinity. This isn’t just another AI model. This is the best video generation model on the market. Photorealism. Cinematic motion. Unparalleled consistency. And now, it’s in your hands.

VEO 2 is here. Google DeepMind’s most advanced AI video model—now live on Nfinity. This isn’t just another AI model. This is the best video generation model on the market. Photorealism. Cinematic motion. Unparalleled consistency. And now, it’s in your hands.

NFINITY AI

24,479 Aufrufe • vor 1 Jahr

This video is a reminder that data is what truly makes a model perform at its best. Bytedance’s latest whitepaper, Omnihuman, showcases human-like video generation like never before. Here’s how other models Luma , Kling AI , Runway , Hailuo AI (MiniMax) react to the same image/prompt. 👇 Comment which model did it best!

This video is a reminder that data is what truly makes a model perform at its best. Bytedance’s latest whitepaper, Omnihuman, showcases human-like video generation like never before. Here’s how other models Luma , Kling AI , Runway , Hailuo AI (MiniMax) react to the same image/prompt. 👇 Comment which model did it best!

OpenLedger

17,398 Aufrufe • vor 1 Jahr

Here’s how to pick your perfect AI model 👇 ✔ Gemini 3.0 – best for devs, agents & long video analysis. ✔ ChatGPT 5.1 – best for personalization & adaptive reasoning. ✔ Grok 4.1 – best for creative writing & emotional tone. Use: → Gemini for deep work. → ChatGPT for daily tasks. → Grok for creative flow. Save this — it’s your AI toolkit for 2025. Want the SOP? DM me. 💬

Here’s how to pick your perfect AI model 👇 ✔ Gemini 3.0 – best for devs, agents & long video analysis. ✔ ChatGPT 5.1 – best for personalization & adaptive reasoning. ✔ Grok 4.1 – best for creative writing & emotional tone. Use: → Gemini for deep work. → ChatGPT for daily tasks. → Grok for creative flow. Save this — it’s your AI toolkit for 2025. Want the SOP? DM me. 💬

Julian Goldie SEO

19,058 Aufrufe • vor 10 Monaten

Today we're launching FilmArena [dot] ai. Biggest release we've ever shipped. The problem: a new SOTA AI image & video model drops every week. OpenAI shipped GPT Image 2 literally yesterday. 1000 endpoints, no honest answer to "which one is best right now?" Arena AI and Artificial Analysis cracked LLM benchmarking. But for creative AI, they're solving the wrong problem. There is no "best image-to-video model." Best at what? World building? Action Sequences? Expressions? Every category has a different winner, and it flips weekly. So we benchmarked 40+ SOTA models with 2M+ votes across 190 countries. By subcategory. Re-ranked every week as new models ship. With thousands of real humans. But that's just half of it. Then there's the SANDBOX. Higgsfield and other aggregators put models in one place. But creators still juggle twelve subscriptions to do one job. FilmArena collapses it into one tab. Every frontier model. One interface. Same price. Call the best, or call 3 at once and compare. The AI film stack has been fragmented since day one. Today it isn't. Go try it free: filmarena [dot] ai Already wild results from this week: 1. OpenAI GPT Image 2 (released yesterday) dominates image editing, but Google DeepMind Nano Banana 2 still wins animated 2. C-1 beats Dreamina AI Seedance 2 on animated 3. Veo 3.1 Fast outperforms Veo 3.1 on realistic video And a lot more. Go check it out.

Today we're launching FilmArena [dot] ai. Biggest release we've ever shipped. The problem: a new SOTA AI image & video model drops every week. OpenAI shipped GPT Image 2 literally yesterday. 1000 endpoints, no honest answer to "which one is best right now?" Arena AI and Artificial Analysis cracked LLM benchmarking. But for creative AI, they're solving the wrong problem. There is no "best image-to-video model." Best at what? World building? Action Sequences? Expressions? Every category has a different winner, and it flips weekly. So we benchmarked 40+ SOTA models with 2M+ votes across 190 countries. By subcategory. Re-ranked every week as new models ship. With thousands of real humans. But that's just half of it. Then there's the SANDBOX. Higgsfield and other aggregators put models in one place. But creators still juggle twelve subscriptions to do one job. FilmArena collapses it into one tab. Every frontier model. One interface. Same price. Call the best, or call 3 at once and compare. The AI film stack has been fragmented since day one. Today it isn't. Go try it free: filmarena [dot] ai Already wild results from this week: 1. OpenAI GPT Image 2 (released yesterday) dominates image editing, but Google DeepMind Nano Banana 2 still wins animated 2. C-1 beats Dreamina AI Seedance 2 on animated 3. Veo 3.1 Fast outperforms Veo 3.1 on realistic video And a lot more. Go check it out.

Mehul Agarwal

51,701 Aufrufe • vor 5 Monaten

I joined Anthropic last week! It’s obvious to me that we’re bottlenecked not by model capabilities, but by creativity and understanding. I’ll be building demos and prototypes that highlight new capabilities and share what we learn about building using these models at Anthropic. Excited to build with the best team and the best models.

I joined Anthropic last week! It’s obvious to me that we’re bottlenecked not by model capabilities, but by creativity and understanding. I’ll be building demos and prototypes that highlight new capabilities and share what we learn about building using these models at Anthropic. Excited to build with the best team and the best models.

Thariq

165,495 Aufrufe • vor 1 Jahr

Today is Day 11 of 12 Days of Agent Two. Agent Two isn't just Claude under the hood - we get asked this a lot. The truth is - while we use all the state of the art models out there, the Agent's real intelligence comes from its harness: a domain-specific layer built from continuous creative research that shapes how every model is actually used - more about this in the video. But this harness is what makes Agent Two frontier intelligence for creative work - at 4x the speed, and half the price.

Today is Day 11 of 12 Days of Agent Two. Agent Two isn't just Claude under the hood - we get asked this a lot. The truth is - while we use all the state of the art models out there, the Agent's real intelligence comes from its harness: a domain-specific layer built from continuous creative research that shapes how every model is actually used - more about this in the video. But this harness is what makes Agent Two frontier intelligence for creative work - at 4x the speed, and half the price.

Invideo

2,560,489 Aufrufe • vor 1 Monat

As AI models get better, I don't think the next breakthrough is another model. It's having a workspace that remembers the project instead of starting over every time you write a prompt. That's what I like about TapNow Creative OS. It connects the context around the work, which is usually where most of the creative effort actually goes. #TapTV #CreativeOS #TapNow

As AI models get better, I don't think the next breakthrough is another model. It's having a workspace that remembers the project instead of starting over every time you write a prompt. That's what I like about TapNow Creative OS. It connects the context around the work, which is usually where most of the creative effort actually goes. #TapTV #CreativeOS #TapNow

Maria

33,359 Aufrufe • vor 2 Monaten