Design Arena
380 posts
Design Arena
@Designarena
World's first benchmark for real-world design with 3M+ creators and counting. Made by @arcada_labs
Katılım Haziran 2025
9 Takip Edilen9.4K Takipçiler
Grok 4.3 by @xai has been added to Design Arena!
xAI’s newest model, a natively multimodal system built for long-context reasoning and tool-augmented code execution.
English
Our team did a deep dive on where @OpenAI's GPT 5.5 is falling short on frontend.
A quick read with the top tips on pitfalls to avoid when using GPT 5.5 for frontend-related tasks (and we don't talk about purple gradients).
Grace Li@grx_xce
English
Mistral Medium 3.5 by @MistralAI is now on Design Arena!
A flagship 128B model with a 256k context window, delivering powerful reasoning, coding, and instruction-following with flexible effort per request.
Mistral Vibe@mistralvibe
Mistral Medium 3.5, a new flagship model in public preview by @MistralAI that merges instruction-following, reasoning, and coding into a single 128B dense model with a 256k context window and configurable reasoning effort. It's a new default model for Mistral Vibe and Le Chat. Released as open weights, under a modified MIT license.
English
MiMo-V2.5 by @XiaomiMiMo and @Xiaomi has been added to Design Arena!
Built for complex agent and coding tasks, with strong visual reasoning, precise chart understanding, and deep multimodal capabilities.
Xiaomi MiMo@XiaomiMiMo
Xiaomi MiMo-V2.5 Series: Pushing Open-Source Agents Forward 🔸 MiMo-V2.5-Pro, our strongest model yet. A major leap from MiMo-V2-Pro in general agentic capabilities, complex software engineering, and long-horizon tasks, now matching frontier models like Claude Opus 4.6 and GPT-5.4 across most benchmarks (SWE-bench Pro 57.2, Claw-Eval 63.8, τ3-Bench 72.9). It can autonomously complete professional tasks involving 1,000+ tool calls, work that would take human experts days. Tech Blog: mimo.xiaomi.com/blog/mimo-v2.5… 🔸 MiMo-V2.5, native omnimodal with strong agentic capabilities. Pro-level agent performance at roughly half the cost. Improved multimodal perception across image and video understanding, native 1M-token context window, and significantly more efficient inference. Tech Blog: mimo.xiaomi.com/blog/mimo-v2.5 🔗 API & Token Plan: platform.xiaomimimo.com/token-plan
English
Take a closer look into GPT 5.5's performance - now on DesignArena.ai
English
We observed a major leap in performance for GPT 5.5 on Game Development and 3D Design.
GPT 5.5 takes the #1 spot in Game Dev Arena, in the same performance band as Claude Opus 4.7.
This is a jump of 39 Elo points from GPT 5.4 (Medium).
In 3D Design, GPT 5.5 also leaped 27 positions - one of the largest subcategory improvements in this subcategory to date.
English
HappyHorse 1.0 by @HappyHorseATH and @AlibabaGroup is now on Design Arena!
Delivering top-tier motion fidelity with high resolution video and natively synchronized audio, optimized for scalable, production-grade workflows.
English
Design Arena has hit 3.2 million users!
The last nine months have been a ridiculous whirlwind, and we could not be more grateful for everyone who helped make it possible 🤍
We've launched 32+ arenas so far. Which one do you want to see next?
English
BREAKING: Kimi K2.6 takes 1st overall of open weights models on Design Arena!
Kimi K2.6 is in the same performance band as Claude Opus 4.7 - while establishing a new price vs. preference frontier.
Huge congratulations to the @Kimi_Moonshot team!
English
BREAKING: GPT Image 2 takes #1 on Image Arena with an Elo of 1406 on Design Arena!
This is an overwhelming 78 point lead over the second place model, GPT Image 1.5, which also happens to be an OpenAI model.
Well worth the wait. Huge congratulations to the @OpenAI team for establishing the new frontier of text to image generation!
English
Design Arena is headed to ICLR!
If you want to work on the world’s most realistic frontier evals, invent solutions for hard-to-verify domains, and scale a product with 3.1M+ users, we’d love to meet you.
Leave a comment to let us know - coffee & swag on us :)
English