World's first benchmark for real-world visuals with 7M+ creators and counting. Made by @intelligence_ai
Joined June 2025
- Tweets816
- Following16
- Followers25K
- Likes1.8K
DesignArena retweeted
Canva’s first-ever image model has debuted at #4 on @DesignArena
This makes @canva the #2 AI image lab in the world, behind only @OpenAI
An incredible achievement from a very hardworking and talented team pushing the boundaries of what design companies accomplish in frontier AI research
Huge congratulations to @MelanieCanva and the rest of the @canva team!
Canva Craft, the first ever image model by @canva, takes the #4 spot on DesignArena's Image leaderboard. This makes Canva the #2 Image Lab after @OpenAI!
Notably, it wins most often on photorealistic product and object shots, setting up studio-style lighting and detailed material textures on a single hero object. It also ranks #1 on the Portrait and Landscape subcategories.
Congrats to the @canva team on the launch!
DesignArena retweeted
Canva Craft debuted as the world's 4th most advanced image generation model on @DesignArena with an Elo score of 1340.
It delivers exceptional visual quality and state-of-the-art text rendering, outperforming some of the world's leading frontier models.
DesignArena retweeted
Introducing Canva Craft 🚀
Extraordinary image generation is now available to everyone, powered by our first frontier model built specifically for design.
With Craft, Canva is now the world's second most advanced AI lab for image generation on @DesignArena's global leaderboard.
See what it can do 👇
DesignArena retweeted
Watch the full animated video here: youtu.be/tGE8D6xwCSU
DesignArena retweeted
HeyGen has always been about putting yourself on camera with the highest quality avatars.
Now HeyGen Video 1.0 handles the rest of the shot: the product close-up, the b-roll, the cutaway. Same standard for quality and speed, across all of video.
Try it: platform.heygen.com/models/h…
BREAKING: HeyGen Video 1.0 (1080p, ultraquality) by @HeyGen, a post-trained model on MiniMax H3 by @MiniMax_AI, ranks #3 on both Design Arena's Video and Image to Video leaderboards, making HeyGen the #2 Video lab overall!
In Video, HeyGen Video 1.0 sits just behind Gemini Omni Flash by @GoogleDeepMind and ahead of Wan 3.0 by @Alibaba_Wan. In Image to Video, it also sits just behind MiniMax H3 Max by @MiniMax_AI, while generating faster than 71% of models.
Congrats to the @HeyGen team!
DesignArena retweeted
Frontier Slides, super fast ;)
BREAKING: Replit by @Replit ranks at #2 on Slides Arena with an Elo of 1279!
It is the highest-rated slides builder under 8 minutes and generates decks ~24% faster than #1, establishing a new Pareto frontier for Speed vs. Preference. Replit places ahead of Gamma 5 by @GammaApp, Manus 1.6 by @ManusAI, and Claude Opus 4.6 by @Anthropic, trailing only Playyy.
Congrats to the @Replit team!
DesignArena retweeted
BREAKING: SpaceXSI's newly released Grok Voice 3.0 ranks #1 across AudioArena's human-speech benchmarks, beating every other model tested:
🥇 Overall Pass Rate: 85.7%
🥇 Assistant Bench Pass Rate: 92.4%
🥇 Grocery Bench Pass Rate: 92.2%
DesignArena retweeted
We found in the thinking summaries that Opus 5.5 structures its thinking and executes more like a "builder", while Astra approaches problems more like a "designer". Go check out the new video now!
@OpenAI's GPT-6 Astra hedges ("maybe", "might", "it seems") about 20x as often as @AnthropicAI's Claude Opus 5.5. Opus usually weighs a few options and commits early, in about 4 out of 5 summaries as opposed to Astra's 1 in 4.
We read 324 of their thinking summaries on Design Arena to see how each one actually goes about building a game. Astra works more like a designer, Opus more like a builder.
Full video in the replies.
DesignArena retweeted
P-Video-2-Pro (Cost) lands on the Preference × Price Pareto frontier on @DesignArena, with pricing starting at just $0.01/s.
That holds for both Text-to-Video and Image-to-Video, putting Cost among the strongest price–preference tradeoffs on the benchmark.
At $0.01/s for 480p and $0.025/s for 768p, it’s the cheapest P-Video-2-Pro mode, while still averaging around 10 seconds per generation, nearly 10× faster than the average video model.
DesignArena retweeted
DeepSeek-V4.1-Flash by @deepseek_ai is back in the top 10, but what's crazier is that 6 out of the 7 models on the Price vs Preference Pareto frontier are all open weights
BREAKING: DeepSeek‑V4.1‑Flash takes 6th overall on Design Arena with an Elo of 1347!
This marks a 39-position jump over the next-highest DeepSeek model - and DeepSeek’s return to a top-10 placement on Design Arena.
The model ranks in the same performance band as Claude Fable 5.1 on real-world frontend design tasks.
Congratulations to the @deepseek_ai team!
DesignArena retweeted
GLM‑5.3‑Flash scores a preliminary Elo of 1343, landing 6th overall in the Design Arena rankings!🚀 Exciting benchmark for our cost‑efficient, natively multimodal model.
Which multimodal or agentic use‑case are you eager to build with it? 🤔
BREAKING: GLM-5.3 Flash by @Zai_org debuts at 6th overall on Design Arena with a preliminary Elo of 1343.
This places the MIT-licensed, natively multimodal model in the same performance band as GLM-5.3 - and ahead of Claude Fable 5 and Muse Spark 1.2.
At $0.15/1M input tokens and $0.50/1M output tokens, it pairs strong performance with highly competitive pricing.
Stay tuned for its performance across our agentic and multimodal evaluations!
Congratulations to the @Zai_org team!
DesignArena retweeted
Creativity is searching for the best ideas. And the only way to find the best ideas is to explore many ideas.
I hope we can bring more creativity and beauty to the world by pushing the Pareto frontier of quality × speed × cost for image generation with P-Image-Ideogram.
Built by the @PrunaAI and @ideogram_ai and evaluated by @DesignArena.
DesignArena retweeted
last week we found K3 explaining unsplash IDs mid-CoT, like it knew what the photo looked like from just ID
tech report today: MoonViT-V2 was trained from scratch with next-token prediction, not contrastive
it knew what the Unsplash id looked like because it had to predict the id from the image
DesignArena retweeted
Kimi K3 by @Kimi_Moonshot really outperforms in 3D landscapes and scenes - here are 11 examples showing why it places 1st:
BREAKING: Kimi K3 by @Kimi_Moonshot is 1st overall on 3D Design with an Elo of 1450.
This is a 6 position and 108 Elo jump from @Kimi_Moonshot's previous model, Kimi K2.6. This performance puts Kimi K2.6 82 Elo ahead of Claude Fable 5 by @AnthropicAI in 2nd and 87 Elo ahead of GLM 5.2 by @Zai_org in 3rd.
Congratulations to the @Kimi_Moonshot team on this accomplishment!
DesignArena retweeted
Will you be at ICML?
If you’re current obsessions include:
• building evals from production data
• verifying “non-verifiable” domains
• RLHF/post-training/RL(insert letter)F
• image/video generation
• real-world benchmarks
DM me if you’ll be in Seoul! I know a night market with the best tanghulu, and I have some events to invite you to :)
