Design Arena (@Designarena) / X

Design Arena

483 posts

Design Arena

@Designarena

World's first benchmark for real-world design with 4M+ creators and counting. Made by @intelligence_ai

Joined June 2025

Design Arena
@Designarena
16h
Kimi-K2.7-Code by @Kimi_Moonshot is now available on Design Arena! Built upon Kimi K2.6, Kimi-K2.7-Code introduces improvements in coding and agent performance, reasoning efficiency, and long-horizon coding, marking it as their strongest coding model yet. Congrats to the
Kimi.ai
@Kimi_Moonshot
Jun 12
🌘 Kimi-K2.7-Code, our latest coding model, is now released and open-sourced! 🔷 Improved coding & agent performance over K2.6: +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, and +31.5% on MLS Bench Lite. 🔷 Reasoning efficiency: Less overthinking, with 30% lower
12K
Design Arena
@Designarena
18h
Article
Reve 2.0 establishes Reve as the top independent foundation image model lab
We are excited to introduce Reve 2.0 – Reve’s most capable image generation model to date. With this release, Reve becomes the highest-ranked independent foundation image model lab on Design Arena....
2.5K
Design Arena
@Designarena
19h
We will continue monitoring Opus 4.8 performance and how it compares to other models. Fable analysis coming soon. Congratulations to the @AnthropicAI team on the launch, and try out Opus 4.8 for free on DesignArena.ai.
Design Arena
From designarena.ai
485
Design Arena
@Designarena
19h
Replying to @Designarena
What this means for model selection Opus 4.8 is a step backward for UI-focused, single-turn tasks. It's worse than Opus 4.7 in both workflow and agentic settings, and substantially worse in single-turn pipelines. For teams choosing a Claude model for design work, Opus 4.7, Opus
512
Design Arena
@Designarena
19h
Replying to @Designarena
But there is a bright spot: Opus 4.8 is very good at backend! Opus 4.8 has real strengths in database design, API scaffolding, and auth implementation, as is shown by holding the 1st position on Design Arena’s Agentic Web Dev Backend Evaluation. Since these are easily checked
414
Design Arena
@Designarena
19h
Replying to @Designarena
This may be a direct result of Opus 4.8’s over-optimization on tool use, as it rarely uses tools that write files directly and instead prefers to use bash commands that directly create files. Since these commands require intricate escaping, it’s easy to make these sorts of
436
Design Arena
@Designarena
19h
Replying to @Designarena
Model Behavior #3: The Return of Anti-Patterns We also see a significant regression in terms of the anti-patterns that Claude Opus 4.8 uses in comparison to Opus 4.7. The model tends to use grid overlays (5.3% of generations) and floating/bobbing hero images (7.4% of
443
Design Arena
@Designarena
19h
Replying to @Designarena
Model Behavior #2: Missing or Broken Outside Sources In hero images where other models interface with common CDNs like Unsplash, Opus 4.8 simply creates supersized emojis and uses them as hero images. This behavior showed up in over 18% of generations and dropped win rates by
374
Design Arena
@Designarena
19h
Replying to @Designarena
While this could be a marker of getting more done with less, Opus 4.8 just does less. This is one of the first signals of agent-based optimization, as shorter outputs lead to faster iteration times for agent deployments.
391
Design Arena
@Designarena
19h
Replying to @Designarena
Model Behavior #1: Shorter code outputs Opus simply generates less than other models in single-turn deployments. In the same workflow-based test conducted across 2,022 generations, Opus generates an average of 67% less lines of code and 61% less characters than its competitors
418
Design Arena
@Designarena
19h
Replying to @Designarena
So why didn't Opus 4.8 make the top 20 for single-turn web dev? To answer this question, we conduct a case-by-case error analysis on both single-turn and multi-turn deployments of Opus 4.8. We notice the following three model behaviors indicative of agent workflow optimization
561
Design Arena
@Designarena
19h
Replying to @Designarena
For context, a non-agentic arena tests whether a model can create one simple web page in a single attempt, usually as one HTML file, as is the case for our non-agentic web dev leaderboard. An agentic arena tests whether a model can work more like a developer over several steps,
747
Design Arena
@Designarena
19h
Opus 4.8’s hyperfocus on agents may be making it worse at design. Opus 4.8 ranks 23rd overall on single-turn HTML Web Dev, a dramatic regression from Fable (1st), Opus 4.6 (2nd), and Opus 4.7 (3rd). This was particularly surprising as @AnthropicAI models have held the top spots
12K