正在加载视频...

视频加载失败

返回首页

Announcing Artificial Analysis Video Arena - the first crowdsourced comparison for Text to Video models Text to Video models are accelerating rapidly and crossing quality thresholds every month. We created Video Arena to compare them using the only source of truth for visual media - human preference! Video Arena...

ArtificialAnlys's profile picture

Artificial Analysis

122,095 subscribers

27,108 次观看 • 2 年前 •via X (Twitter)

科学技术教育财经
LIVE

Anya Rossi• Live Now

Private livecam show

8 条评论

Artificial Analysis 的头像
Artificial Analysis2 年前

Contribute to the Video Arena! 🔗

Simon Smith 的头像
Simon Smith2 年前

Does it account for generation time or just quality?

Artificial Analysis 的头像
Artificial Analysis2 年前

Just quality for the Arena this week but we'll we back soon with full performance and cost coverage

Tristan Rhodes 的头像
Tristan Rhodes2 年前

Yes! I love seeing your team expand the areas you cover. :)

Andrew Arkins 的头像
Andrew Arkins2 年前

Great idea!

David Hendrickson 的头像
David Hendrickson2 年前

This is great to see! I've looked at but their models don't seem to update very often so its nice to see another alternative to compare these text to video sources.

Prashant 的头像
Prashant2 年前

genAI is incomplete without video. this is great to see that your team is putting effort in bringing transparent analysis of the popular tools

Alfred Rotors 的头像
Alfred Rotors2 年前

I was wondering when you would do this - fantastic! I’ll definitely give this a go.

相关视频

Grok Imagine Video is now dominating the Artificial Analysis Arena #1 in both Text→Video and Image→Video Outranking Veo 3.1, Sora 2 and Kling 2.6 Pro in every way - Best overall quality - Fastest generation times - Lowest cost-to-performance ratio - Native audio-video support xAI is leading the next wave of AI video generation
0:30

Grok Imagine Video is now dominating the Artificial Analysis Arena #1 in both Text→Video and Image→Video Outranking Veo 3.1, Sora 2 and Kling 2.6 Pro in every way - Best overall quality - Fastest generation times - Lowest cost-to-performance ratio - Native audio-video support xAI is leading the next wave of AI video generation

X Freeze

16,972 次观看 • 9 个月前

🎇 Video Model Comparison: Image2Video Video Model Comparison: Image2Video Same input image + text prompt on each model: • Pika 2.0 • PixVerse 3.5 • Runway Gen-3 • Kling AI 1.6 • Luma Dream Machine • Hailuo MiniMax I used the same Midjourney image and text prompt in each model and chose my favorite results.
1:00

🎇 Video Model Comparison: Image2Video Video Model Comparison: Image2Video Same input image + text prompt on each model: • Pika 2.0 • PixVerse 3.5 • Runway Gen-3 • Kling AI 1.6 • Luma Dream Machine • Hailuo MiniMax I used the same Midjourney image and text prompt in each model and chose my favorite results.

Heather Cooper

36,110 次观看 • 1 年前

Runway released Gen-4.5 today and it is already ranked first on the Video Arena leaderboard. We sat down with CEO Cristóbal Valenzuela to discuss how a small team is currently beating Google and Meta in the race for state-of-the-art video generation. The full episode is below!
1:08

Runway released Gen-4.5 today and it is already ranked first on the Video Arena leaderboard. We sat down with CEO Cristóbal Valenzuela to discuss how a small team is currently beating Google and Meta in the race for state-of-the-art video generation. The full episode is below!

Weights & Biases

367,588 次观看 • 11 个月前

🚨 How does Adobe Firefly Video stack up against other AI video models? I ran the same prompts on: • Runway Gen-3 • Hailuo AI’s MiniMax • Luma AI Dream Machine The results were fascinating. 5 Examples below:
0:54

🚨 How does Adobe Firefly Video stack up against other AI video models? I ran the same prompts on: • Runway Gen-3 • Hailuo AI’s MiniMax • Luma AI Dream Machine The results were fascinating. 5 Examples below:

Heather Cooper

73,234 次观看 • 2 年前

Arena AutoEval can quickly evaluate new models, allowing model labs to leverage results faster. It compresses the evaluation feedback loop from weeks to hours, enabling rapid, human-preference-based insight into a model’s capabilities. For more details, see the full video in the post below.
1:35

Arena AutoEval can quickly evaluate new models, allowing model labs to leverage results faster. It compresses the evaluation feedback loop from weeks to hours, enabling rapid, human-preference-based insight into a model’s capabilities. For more details, see the full video in the post below.

Arena.ai

21,583 次观看 • 3 个月前

1. Vidnoz image to video Vidnoz's Image to Video feature now includes several top models, like Veo3, Kling, Hailuo, and Runway. Can also use Nano Banana with the Image Generator Kling + Veo3 + Hailuo + Runway available 🔗
0:22

1. Vidnoz image to video Vidnoz's Image to Video feature now includes several top models, like Veo3, Kling, Hailuo, and Runway. Can also use Nano Banana with the Image Generator Kling + Veo3 + Hailuo + Runway available 🔗

Arpita Trisha

165,637 次观看 • 11 个月前

Introducing Playjump Video Generator. Tired of juggling multiple tools? Access the top video models - Runway Luma Kling AI #minimax All in one place. Stop switching tabs. Pay for only one tool. Experiment faster. 50% OFF for the first 100 subscribers.
0:43

Introducing Playjump Video Generator. Tired of juggling multiple tools? Access the top video models - Runway Luma Kling AI #minimax All in one place. Stop switching tabs. Pay for only one tool. Experiment faster. 50% OFF for the first 100 subscribers.

Sudharshan

22,461 次观看 • 2 年前

SITUATION EXPLAINED: MiniMax released H3 with open weights, and it's already #1 in video editing. • Priced at $7.80 per minute of 2K video, against Seedance 2.0 at $22.45 and Kling 3.0 at $20.16 • It ranks #1 on Artificial Analysis for video editing, #2 for text-to-video behind Gemini Omni Flash, and #3 for image-to-video • H3 takes text, images, video, and audio in a single context and generates 5-15 second clips at native 2K, 24fps, with native stereo audio • MiniMax is releasing the weights under its Community License within days, which would make it the strongest open-weights video model by a wide margin • It launched the same week ByteDance rolled out Seedance 2.5, which now generates 30-second 4K video from a single prompt • Seedance 2.5's face consistency across a full 30 seconds is the visible jump, earlier models drifted into a different face partway through • Voices are still the obvious tell, the video reads as real long before the audio does • Smaller labs building purpose-built video models are now beating frontier labs at this specific task Theo Jaffee: "This is gonna be one of the biggest examples of things that people are gonna do with these models, historical simulations, basically. Nostalgia videos for zoomers."
7:17

SITUATION EXPLAINED: MiniMax released H3 with open weights, and it's already #1 in video editing. • Priced at $7.80 per minute of 2K video, against Seedance 2.0 at $22.45 and Kling 3.0 at $20.16 • It ranks #1 on Artificial Analysis for video editing, #2 for text-to-video behind Gemini Omni Flash, and #3 for image-to-video • H3 takes text, images, video, and audio in a single context and generates 5-15 second clips at native 2K, 24fps, with native stereo audio • MiniMax is releasing the weights under its Community License within days, which would make it the strongest open-weights video model by a wide margin • It launched the same week ByteDance rolled out Seedance 2.5, which now generates 30-second 4K video from a single prompt • Seedance 2.5's face consistency across a full 30 seconds is the visible jump, earlier models drifted into a different face partway through • Voices are still the obvious tell, the video reads as real long before the audio does • Smaller labs building purpose-built video models are now beating frontier labs at this specific task Theo Jaffee: "This is gonna be one of the biggest examples of things that people are gonna do with these models, historical simulations, basically. Nostalgia videos for zoomers."

MTS

57,168 次观看 • 3 个月前

We were impressed to see Runway's latest model beat much larger competitors on the Artificial Analysis text to video leaderboard - we did a quick interview with Cristóbal Valenzuela on how he did it. Link to podcast episode below
1:08

We were impressed to see Runway's latest model beat much larger competitors on the Artificial Analysis text to video leaderboard - we did a quick interview with Cristóbal Valenzuela on how he did it. Link to podcast episode below

Lukas Biewald

148,739 次观看 • 11 个月前

🚨 BREAKING NEWS 🚨 A Chinese video AI just dropped, and it’s already shaking up the video world. Meet #MiniMax, the AI that’s set to revolutionize the game and claim its place in the video AI arena. Check out this 2-minute official demo, created entirely in Text to Video mode. You’re not ready for this! 🎥🔥
1:54

🚨 BREAKING NEWS 🚨 A Chinese video AI just dropped, and it’s already shaking up the video world. Meet #MiniMax, the AI that’s set to revolutionize the game and claim its place in the video AI arena. Check out this 2-minute official demo, created entirely in Text to Video mode. You’re not ready for this! 🎥🔥

Pierrick Chevallier | IA

98,254 次观看 • 2 年前

A new chapter of creativity begins. Introducing GEN-3 Alpha - The first of a series of new models built by creatives for creatives. Video generated with Runway's new Text-2-Video model. Coming soon.
1:51

A new chapter of creativity begins. Introducing GEN-3 Alpha - The first of a series of new models built by creatives for creatives. Video generated with Runway's new Text-2-Video model. Coming soon.

Nicolas Neubert

112,271 次观看 • 2 年前

🤩 Introducing Background Removal Arena: Compare & Test the Best Background Removal Models ⚔️ An AI arena to rank the top background removal tools based on community votes. A transparent, open, and reliable resource for community as the Leaderboard and Voting data are made public too.
0:23

🤩 Introducing Background Removal Arena: Compare & Test the Best Background Removal Models ⚔️ An AI arena to rank the top background removal tools based on community votes. A transparent, open, and reliable resource for community as the Leaderboard and Voting data are made public too.

Gradio

25,214 次观看 • 1 年前

Video Model Comparison: Image to video I updated an older comparison with a new image and prompt to test in several models: • Pika 2.2 • PixVerse 4 • Runway Gen-4 • Google Veo 3 • OpenAI Sora • Kling 2.1 Pro • Luma Ray2 • Hailuo I2V I used the same prompt and Midjourney image in each model 2-3 times and chose my favorite results below:
1:12

Video Model Comparison: Image to video I updated an older comparison with a new image and prompt to test in several models: • Pika 2.2 • PixVerse 4 • Runway Gen-4 • Google Veo 3 • OpenAI Sora • Kling 2.1 Pro • Luma Ray2 • Hailuo I2V I used the same prompt and Midjourney image in each model 2-3 times and chose my favorite results below:

Heather Cooper

98,406 次观看 • 1 年前

🎬 Video Model Comparison: Text to video • Google Veo 2 • OpenAI Sora • Hunyuan Video • Pika 2.1 • Alibaba Wanx 2.1 • Runway Gen-3 • Kling 1.6 • Luma Ray2 • Hailuo T2V-01 I used the same prompt on each model for 2 generations and chose the best results below. Prompt: A majestic white tiger prowling silently through a dense jungle, sunlight piercing through the foliage to illuminate its fur; shot with a telephoto lens for depth, using soft natural lighting and creating a mysterious yet tranquil atmosphere. Prompt credit: LudovicCreator Overall, the results are impressive for each one. We have many choices for AI video! I could have tested more models, but this visual is crowded enough. Drop your results in the comments 👇
1:02

🎬 Video Model Comparison: Text to video • Google Veo 2 • OpenAI Sora • Hunyuan Video • Pika 2.1 • Alibaba Wanx 2.1 • Runway Gen-3 • Kling 1.6 • Luma Ray2 • Hailuo T2V-01 I used the same prompt on each model for 2 generations and chose the best results below. Prompt: A majestic white tiger prowling silently through a dense jungle, sunlight piercing through the foliage to illuminate its fur; shot with a telephoto lens for depth, using soft natural lighting and creating a mysterious yet tranquil atmosphere. Prompt credit: LudovicCreator Overall, the results are impressive for each one. We have many choices for AI video! I could have tested more models, but this visual is crowded enough. Drop your results in the comments 👇

Heather Cooper

256,264 次观看 • 1 年前

✨Spotlight: Top 4 Code Arena open models Open models are moving fast, and this community is directly shaping how that progress shows up in real use. Your builds, votes, and experiments surface what frontier models can actually do in practice. To celebrate the momentum, we’re spotlighting the top open models in Code Arena (WebDev) 🧵👇 🔥 MiniMax (official) — MiniMax-M2.1 🤖 Z.ai — GLM-4.7 ✨ DeepSeek — Deepseek-v3.2-thinking 🚀 Xiaomi MiMo — Mimo-v2-flash (non-thinking) Let’s keep building in the open and raising the bar together 🚀
1:07

✨Spotlight: Top 4 Code Arena open models Open models are moving fast, and this community is directly shaping how that progress shows up in real use. Your builds, votes, and experiments surface what frontier models can actually do in practice. To celebrate the momentum, we’re spotlighting the top open models in Code Arena (WebDev) 🧵👇 🔥 MiniMax (official) — MiniMax-M2.1 🤖 Z.ai — GLM-4.7 ✨ DeepSeek — Deepseek-v3.2-thinking 🚀 Xiaomi MiMo — Mimo-v2-flash (non-thinking) Let’s keep building in the open and raising the bar together 🚀

Arena.ai

16,798 次观看 • 10 个月前

Are open source models catching up to proprietary models? We’ve looked back at 3 years of Arena’s data to show how the race has evolved. For comparison, we’ve taken the top 20% of the models and uncovered the following: - Before mid 2024: The gap was between 100-150 points - In the second half of 2024, the gap rapidly narrowed to ~50 points - This was driven by the fact that proprietary models have not significantly improved between early 2023 and November 2024 - hovering around the 1350 score for the top 20% of proprietary models - Then since Jan 2025, we saw a parallel improvement in both proprietary and open source models - Meaning that for the last ~14 months the gap stayed steady at around 50-60 points For context, 50 points is the gap between the 1st and 20th place in the Overall leaderboard Today, proprietary models take up the first 20 spots on the Text Arena, with Anthropic, Google DeepMind , xAI and OpenAI leading in the rankings. The top open source models are ranked #20 (GLM-5 by Z.ai ), #23 (Kimi-K2.5-Thinking by Kimi.ai ) and #27 (Qwen3.5-397b-a17b by Qwen ).
0:21

Are open source models catching up to proprietary models? We’ve looked back at 3 years of Arena’s data to show how the race has evolved. For comparison, we’ve taken the top 20% of the models and uncovered the following: - Before mid 2024: The gap was between 100-150 points - In the second half of 2024, the gap rapidly narrowed to ~50 points - This was driven by the fact that proprietary models have not significantly improved between early 2023 and November 2024 - hovering around the 1350 score for the top 20% of proprietary models - Then since Jan 2025, we saw a parallel improvement in both proprietary and open source models - Meaning that for the last ~14 months the gap stayed steady at around 50-60 points For context, 50 points is the gap between the 1st and 20th place in the Overall leaderboard Today, proprietary models take up the first 20 spots on the Text Arena, with Anthropic, Google DeepMind , xAI and OpenAI leading in the rankings. The top open source models are ranked #20 (GLM-5 by Z.ai ), #23 (Kimi-K2.5-Thinking by Kimi.ai ) and #27 (Qwen3.5-397b-a17b by Qwen ).

Arena.ai

22,447 次观看 • 7 个月前

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.
0:36

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.

AK

143,565 次观看 • 3 年前

Introducing Higgsfield Draw-to-Video. RIP Prompts. Turn your sketch into an absolute cinema. Works with all our video models: MiniMax, Veo 3 & Seedance Pro. This is possible ONLY in Higgsfield. Retweet to unlock the full capacity of the best video models in your DMs.
0:47

Introducing Higgsfield Draw-to-Video. RIP Prompts. Turn your sketch into an absolute cinema. Works with all our video models: MiniMax, Veo 3 & Seedance Pro. This is possible ONLY in Higgsfield. Retweet to unlock the full capacity of the best video models in your DMs.

Higgsfield AI 🧩

5,413,742 次观看 • 1 年前

HeyGen Video, now in 2K resolution. #1 on OpenRouter's video leaderboard by usage, with quality on par with the leading models at a fraction of the price.
0:39

HeyGen Video, now in 2K resolution. #1 on OpenRouter's video leaderboard by usage, with quality on par with the leading models at a fraction of the price.

HeyGen Developers

1,036,197 次观看 • 1 个月前