TL;DR
- 💰 Best expensive model: Claude Opus 4.8
- ⚖️ Best balanced model: GPT-5.3 codex
- 🪙 Best cheap model:
Kimi K2.6GPT-5.3 chat - ⛔️ Not for Page Builder: Kimi K2.7
Kimi K2.6 tend to overthink the task even with lowest possible effort. I will review the system prompt, maybe it's possible to speedup Kimi using system prompt?
Kimi-K2.7 generates even more tokens! Get ready to wait for an answear for 2 minutes!
Let's battle test AI Composer element with different prompts to see which models produce the best outcome for ecommerce stores.
1. Making a section similar to provided image
Let's steal some designs first 😈. I'll use the following prompt with a few different images:
Create a section based on provided image
Image 1
A clean, minimalistic, flat layout with sharp rectangular edges:
Claude Opus 4.7, 4.8, and GPT-5.5 provided accurate and consistent results. They properly understood the key aspects of the source design (flat layout, sharp edges, striped full-width sections) and successfully recreated them. Are they worth their price in this test? No, because cheaper models was able to provide nice results too.
Claude Sonnet 4.6 and GPT-5.3-codex were able to deliver the same level of quality at a lower cost.
It's worth noting the difference between GPT-5.3-chat and GPT-5.3-codex. The chat model was more random and tended to add big border radius and shadows. Codex, on the other hand, used more tokens and was therefore more expensive. In fact its price was on the same level as GPT-5.4 model.
GPT-5.4 and Kimi-K2.6 models produced good results, but both struggled with details. GPT-5.4 didn't made full-width sections, Kimi-K2.6 didn't notice striped-rows and sometimes forgot to code three rows and produced two instead.
Hovewer, I do recommend trying Kimi-K2.6 because of its price.
Comparison table
| Model | Design | Accuracy | Consistency | Speed | Cost |
|---|---|---|---|---|---|
| Claude-Opus-4.7 | ★★★★★ | ★★★★★ | ★★★★★ | 18s | $0,058 |
| Claude-Opus-4.8 | ★★★★★ | ★★★★★ | ★★★★★ | 17s | $0,0554 |
| Claude-Sonnet-4.6 | ★★★★★ | ★★★★★ | ★★★★★ | 23s | $0,0276 |
| GPT-5.3-codex | ★★★★★ | ★★★★★ | ★★★★★ | 23s | $0,0252 |
| GPT-5.3-chat | ★★★★☆ | ★★★☆☆ | ★★★★☆ | 15s | $0,0166 |
| GPT-5.4 | ★★★★★ | ★★★★☆ | ★★★★☆ | 19s | $0,0242 |
| GPT-5.5 | ★★★★★ | ★★★★★ | ★★★★★ | 28s | $0,0531 |
| Kimi-K2.6 | ★★★★☆ | ★★★★☆ | ★★★☆☆ | 18s | $0,00579 |
View Screenshots
Image 2
Modern, fullscreen split-grid layout:
Claude Opus 4.7, 4.8, and GPT-5.5 proved their status again. They did the clean and accurate job. However, cheaper models were on par with them again.
GPT-5.3-chat and Kimi-K2.6 were able to deliver the same level of quality at a lower cost. Claude-Sonnet-4.6 wasn't 100% accurate, in all tests.
GPT-5.3-codex and GPT-5.4 had the same issue in this test. They both didn't made the full-width layout.
Comparison table
| Model | Design | Accuracy | Consistency | Speed | Cost |
|---|---|---|---|---|---|
| Claude-Opus-4.7 | ★★★★☆ | ★★★★★ | ★★★★★ | 23s | $0,0655 |
| Claude-Opus-4.8 | ★★★★★ | ★★★★★ | ★★★★★ | 17s | $0,0587 |
| Claude-Sonnet-4.6 | ★★★★☆ | ★★★★★ | ★★★★☆ | 17s | $0,0281 |
| GPT-5.3-codex | ★★★★★ | ★★★★☆ | ★★★☆☆ | 25s | $0,0269 |
| GPT-5.3-chat | ★★★★☆ | ★★★★★ | ★★★☆☆ | 17s | $0,0152 |
| GPT-5.4 | ★★★★☆ | ★★★★☆ | ★★★★☆ | 16s | $0,0246 |
| GPT-5.5 | ★★★★★ | ★★★★★ | ★★★★★ | 35s | $0,0668 |
| Kimi-K2.6 | ★★★★★ | ★★★★★ | ★★★★☆ | 21s | $0,00716 |
View Screenshots
Detailed described sections
Test 1. Free shipping banner
Prompt: Free shipping stripe-banner for order above 30$. Vivid colors, high contrast, funky style
GPT-5.5 is the king here! I can't say for now if it's a prompt that won the lottery, or this model is unbeatable in creative tasks. The next tests will help to understand.
Gemini-3.1-pro is the runner up here. It produces nice funky designs but, unfortunately, it's too slow.
Kimi-K2.6 didn't made it. It's time to generate the response was more that 2-3 minutes! True token eater.
Comparison table
| Model | Design | Speed | Cost |
|---|---|---|---|
| Claude-Opus-4.7 | ★★★☆☆ | 19s | $0,0472 |
| Claude-Opus-4.8 | ★★★☆☆ | 15s | $0,0476 |
| Claude-Sonnet-4.6 | ★★★☆☆ | 23s | $0,0321 |
| Gemini-3.1-pro | ★★★★☆ | 42s | $0,0557 |
| GPT-5.3-codex | ★★★☆☆ | 19s | $0,0217 |
| GPT-5.3-chat | ★☆☆☆☆ | 10s | $0,00953 |
| GPT-5.4 | ★★☆☆☆ | 6s | $0,0197 |
| GPT-5.5 | ★★★★★ | 22s | $0,0548 |
