How OpenAI’s Sol Finally Learned Design Taste
We benchmarked GPT-5.6 Sol on Design Arena’s Web Design (Non-Agentic) Arena , and we were surprised to find that it ranks 1st overall. This is 18 places higher than its predecessor GPT-5.5, and is the first time an OpenAI model has placed first on this leaderboard. We dug deeper and broke down the deployments of GPT-5.6 Sol to track which frontend coding tasks the model excels at:<br>GPT-5.6 Sol appears to recognize and actively suppress common AI design anti-patterns. We projected the CLIP embeddings of 1,000 websites generated by GPT-5.6 using UMAP to visualize the model’s design manifold. Shockingly, we found that its design space contains clear gaps where GPT-5.5 produces purple gradients , bento-box layouts, oversized hero text, and offset compositions, suggesting that GPT-5.6 has learned these AI-anti patterns but selectively avoids generating them.<br>It combines strong templates with unusually high personalization. GPT-5.6 Sol starts from proven design structures but adapts them substantially to each prompt, striking a better balance between consistency and variety than either heavily templated or fully unconstrained models.
0:00
/0:16
1×
0:00
/0:38
1×
GPT 5.6 Sol establishes two new Pareto frontiers for both preference vs speed and preference vs price. It is over 2.44x faster than GLM 5.2 (previously ranked 1st) and 36% faster than Claude Fable 5, with a price of $5/$30 per 1 million tokens versus Claude Fable 5’s $10/$50 per 1 million tokens .<br>So what changed in GPT-5.6 Sol’s website outputs?<br>We discovered GPT-5.6 Sol’s design taste has been carefully curated to avoid AI anti-patterns that lead to generic aesthetics. This specialization in design, unique approach to templating, and remarkable multimodal performance places GPT-5.6 Sol first on our single-turn leaderboards.<br>Model Behavior #1: Explicit Avoidance of AI Anti-Patterns<br>In our review of GPT-5.5 three months ago, we identified a set of “design smells” that GPT-5.5 consistently produced. These design smells included large typefaces instead of hero images, unusual layout decisions, and overused purple gradients. We’re happy to say that most of these design smells have completely vanished in GPT-5.6 Sol.<br>Loser indicating Classic AI Design “Smell” #1: Purple & blue gradientsLoser indicating Classic AI Design “Smell” #2: Grid backgroundWhile GPT-5.6 Sol is not the only model to solve the anti-pattern issue, it takes a unique approach that’s worth highlighting. We projected the CLIP embeddings of 1,000 websites generated by GPT-5.6 using UMAP to visualize the model’s design manifold: the region of the larger CLIP embedding space occupied by its generations. Find that visualization below.<br>We were shocked to discover strange holes in the resulting subspace.<br>These holes are not present in other models, such as in the GPT-5.5 visualization below, since most models produce web designs similar to other previously generated designs, with variations only coming from the prompt itself. Since UMAP projection theoretically preserves holes in the manifold (assuming the right projection parameters), finding holes in one model’s design space, yet not in another model’s, signals that GPT-5.6 Sol may have a cluster of designs within those holes that it’s not generating.<br>To figure out what designs are within these holes, we overlapped GPT-5.6 Sol and GPT-5.5’s websites within the same embedding space and conducted the same UMAP projection as earlier. From there, we colored all of the GPT-5.6 Sol generations orange, then stacked those on top of GPT-5.5’s generations. Any regions without orange would be patterns specific to GPT-5.5, while any regions with orange would be specific to GPT-5.6 Sol.
This becomes even clearer if we remove the screenshots and replace GPT-5.5 and GPT-5.6 Sol specific generations with blue and orange dots respectively. This gives us the visualization below, where we can see GPT-5.5 and GPT-5.6 Sol generate mostly similar websites, with GPT-5.6 Sol showing slightly more variance than GPT-5.5. However, there is one major cluster where GPT-5.5 and GPT-5.6 Sol don’t overlap at all: the cluster for websites with purple gradients.<br>While GPT-5.6 Sol produces largely similar designs to GPT-5.5, there is a clear effort when it comes to avoiding many common AI anti-patterns. We see the same effect for other anti-patterns, like bento box layouts, large typefaces in hero images, and offset layouts.<br>This approach is notably different from other models. For example, GLM-5.2 avoids anti-patterns such as large typefaces by learning a set of templates that do not include them. This avoids anti-patterns without creating holes in the generated space since GLM-5.2 simply avoids generating designs with anti-patterns entirely.<br>While GLM-5.2 appears to have avoided learning design anti-patterns at all (and thus avoids producing them), it appears as if GPT-5.6 Sol has learned that specific design anti-patterns...