OpenDesignArena
Find the right AI model for design.
Compare quality, speed, and cost with real evaluations.
Works with 21 agents and includes every ranked model Download and start designing with Claude Haiku 5.5
Best value
Claude Haiku 5.5The best balance of quality, cost and speed.
In this evaluation, Claude Haiku 5.5 achieved 91% of top-ranked GPT-6.1 Sol’s average score, at just 5% of its average cost.
- Cost per artifact
- $0.018vs $0.382
- Evaluation average / 100
- 82.2vs 90.1
Highest score
Fastest delivery
Compare models
Pick two or three models and see all five dimensions on one chart. Different shapes mean different strengths.
Five-dimension profile
Farther out is better on all five axes: stronger results, faster completion, and lower cost.
Mean on each axis across all 20 models
Choose by preference
Balance evaluated quality, cost, and speed to find the model that suits your needs.
- Quality
- 50%
- Cost
- 30%
- Speed
- 20%
- 1 Claude Haiku 5.5 84.2 Average score: 82.2/100; Average cost: $0.018; Average time: 2.5 min
- 2
GPT-6 Luna 82.5 Average score: 83.1/100; Average cost: $0.016; Average time: 4.2 min - 3
DeepSeek V4.1 Flash 78.8 Average score: 81.2/100; Average cost: $0.023; Average time: 5.3 min - 4
MiMo 2.6 Flash 73.6 Average score: 83.5/100; Average cost: $0.029; Average time: 16.0 min - 5 GPT-6 Sol 72.6 Average score: 89.9/100; Average cost: $0.297; Average time: 4.7 min
- 6 GPT-6.1 Sol 70.3 Average score: 90.1/100; Average cost: $0.382; Average time: 6.2 min
- 7
GLM-5.3 Flash-X 70.0 Average score: 80.1/100; Average cost: $0.098; Average time: 8.0 min - 8 Claude Sonnet 5.5 68.9 Average score: 86.8/100; Average cost: $0.574; Average time: 4.1 min
- 9 GPT-5.6 Sol 65.7 Average score: 77.6/100; Average cost: $0.544; Average time: 3.2 min
- 10
Gemini 3.8 Flash 64.7 Average score: 68.9/100; Average cost: $0.210; Average time: 3.8 min - 11 Gemini 4 Argon 63.3 Average score: 81.2/100; Average cost: $0.667; Average time: 6.4 min
- 12
Muse Spark 1.3 63.2 Average score: 66.6/100; Average cost: $0.267; Average time: 3.3 min - 13
MiniMax M3.1 Flash 62.9 Average score: 81.7/100; Average cost: $0.247; Average time: 17.5 min - 14 Muse Wonder 61.3 Average score: 76.2/100; Average cost: $1.25; Average time: 3.3 min
- 15
Grok 4.7 59.6 Average score: 82.9/100; Average cost: $0.662; Average time: 16.3 min - 16 GPT-6 Astra 57.5 Average score: 82.7/100; Average cost: $1.61; Average time: 11.1 min
- 17
Hunyuan H4 Preview 54.6 Average score: 74.6/100; Average cost: $0.418; Average time: 29.2 min - 18
Qwen 3.8-Max 52.3 Average score: 72.0/100; Average cost: $0.595; Average time: 26.4 min - 19 Claude Fable 5.1 52.1 Average score: 80.3/100; Average cost: $3.66; Average time: 12.8 min
- 20
Kimi K3 52.1 Average score: 65.7/100; Average cost: $0.614; Average time: 14.0 min
Choose by use case
Pick a design scenario; each of the five dimensions below recommends one model.
GPT-6.1 Sol
- Avg. score Average scoreHigher is better The mean score across all evaluated artifacts, out of 100.
- 90.1/100
- Avg. requirement Requirement fulfillmentHigher is better Checks whether required pages, content, states, and interactions are present, out of 30.
- 28.0/30
- Avg. design quality Design qualityHigher is better Rates layout, hierarchy, style, color, and image fit, out of 70.
- 62.2/70
- Avg. delivery rate Delivery rateHigher is better The share of evaluated artifacts scoring 80 or above.
- 90.0%
- Mean time Average completion timeLower is better Total execution time across scored artifacts divided by their count.
- 6.2 min
- Mean cost / artifact Cost per artifactLower is better Estimated from official list prices and measured token usage.
- $0.382/run
GPT-6.1 Sol
- Avg. design quality
- 62.2/70
- Avg. score
- 90.1/100
- Avg. delivery rate
- 90.0%
- Avg. requirement
- 28.0/30
- Mean time
- 6.2 min
- Mean cost / artifact
- $0.382/run
DeepSeek V4.1 Flash
- Avg. requirement
- 28.4/30
- Avg. score
- 81.2/100
- Avg. delivery rate
- 57.7%
- Avg. design quality
- 52.8/70
- Mean time
- 5.3 min
- Mean cost / artifact
- $0.023/run
Claude Haiku 5.5
- Mean time
- 2.5 min
- Avg. score
- 82.2/100
- Avg. delivery rate
- 62.2%
- Avg. requirement
- 26.5/30
- Avg. design quality
- 55.7/70
- Mean cost / artifact
- $0.018/run
GPT-6 Luna
- Mean cost / artifact
- $0.016/run
- Avg. score
- 83.1/100
- Avg. delivery rate
- 70.5%
- Avg. requirement
- 25.2/30
- Avg. design quality
- 57.9/70
- Mean time
- 4.2 min
Quality and cost
Compare model performance and the cost of achieving it.
Quality ranking
GPT-6.1 Sol GPT-6 Sol Claude Sonnet 5.5 MiMo 2.6 Flash GPT-6 Luna Grok 4.7 GPT-6 Astra Claude Haiku 5.5 MiniMax M3.1 Flash DeepSeek V4.1 Flash Gemini 4 Argon Claude Fable 5.1 GLM-5.3 Flash-X GPT-5.6 Sol Muse Wonder Hunyuan H4 Preview Qwen 3.8-Max Gemini 3.8 Flash Muse Spark 1.3 Kimi K3 Model quality vs cost
9 models in the pink area cost more and score lower than DeepSeek V4.1 Flash.
Scenario performance
Viewing Web app (Multi-page structure and flows); MiMo 2.6 Flash leads at 93.9, with a 100.0% delivery rate and $0.043 per run.
Viewing Mobile app (Touch experience and responsive layout); Hunyuan H4 Preview leads at 89.5, with a 83.3% delivery rate and $0.404 per run.
Viewing Desktop app (Desktop workflows and complex interactions); GPT-6.1 Sol leads at 93.0, with a 100.0% delivery rate and $0.340 per run.
Viewing Dashboard (Information density and hierarchy); GPT-6.1 Sol leads at 95.6, with a 100.0% delivery rate and $0.365 per run.
Viewing Landing page (Brand expression and conversion); GPT-6.1 Sol leads at 89.8, with a 88.9% delivery rate and $0.349 per run.
Web app ranking
MiMo 2.6 Flash GPT-6.1 Sol GPT-6 Sol Grok 4.7 Claude Sonnet 5.5 GPT-5.6 Sol Claude Fable 5.1 DeepSeek V4.1 Flash MiniMax M3.1 Flash Gemini 4 Argon GPT-6 Luna GLM-5.3 Flash-X Claude Haiku 5.5 GPT-6 Astra Muse Wonder Gemini 3.8 Flash Muse Spark 1.3 Hunyuan H4 Preview Qwen 3.8-Max Kimi K3 Web app · Model quality vs cost
10 models in the pink area cost more and score lower than DeepSeek V4.1 Flash.
Mobile app ranking
Hunyuan H4 Preview GPT-6 Astra GPT-6 Sol GPT-5.6 Sol Claude Sonnet 5.5 Grok 4.7 MiniMax M3.1 Flash Gemini 4 Argon GPT-6 Luna DeepSeek V4.1 Flash Claude Haiku 5.5 Kimi K3 Gemini 3.8 Flash Claude Fable 5.1 GPT-6.1 Sol MiMo 2.6 Flash GLM-5.3 Flash-X Muse Wonder Muse Spark 1.3 Qwen 3.8-Max Mobile app · Model quality vs cost
9 models in the pink area cost more and score lower than DeepSeek V4.1 Flash.
Desktop app ranking
GPT-6.1 Sol Claude Sonnet 5.5 GPT-6 Sol Claude Haiku 5.5 GPT-6 Astra Gemini 4 Argon DeepSeek V4.1 Flash Kimi K3 MiMo 2.6 Flash Muse Wonder Qwen 3.8-Max MiniMax M3.1 Flash GLM-5.3 Flash-X GPT-6 Luna GPT-5.6 Sol Grok 4.7 Muse Spark 1.3 Gemini 3.8 Flash Hunyuan H4 Preview Claude Fable 5.1 Desktop app · Model quality vs cost
11 models in the pink area cost more and score lower than DeepSeek V4.1 Flash.
Dashboard ranking
GPT-6.1 Sol GPT-6 Sol Claude Haiku 5.5 GPT-6 Luna Claude Sonnet 5.5 GPT-6 Astra Claude Fable 5.1 Gemini 4 Argon MiMo 2.6 Flash MiniMax M3.1 Flash GLM-5.3 Flash-X Qwen 3.8-Max Hunyuan H4 Preview Grok 4.7 Muse Wonder GPT-5.6 Sol Muse Spark 1.3 DeepSeek V4.1 Flash Gemini 3.8 Flash Kimi K3 Dashboard · Model quality vs cost
2 models in the pink area cost more and score lower than DeepSeek V4.1 Flash.
Landing page ranking
GPT-6.1 Sol GPT-6 Sol GPT-6 Luna GLM-5.3 Flash-X MiMo 2.6 Flash Claude Sonnet 5.5 Qwen 3.8-Max Grok 4.7 Claude Fable 5.1 DeepSeek V4.1 Flash MiniMax M3.1 Flash GPT-6 Astra Claude Haiku 5.5 Muse Wonder Gemini 4 Argon Hunyuan H4 Preview Kimi K3 GPT-5.6 Sol Muse Spark 1.3 Gemini 3.8 Flash Landing page · Model quality vs cost
9 models in the pink area cost more and score lower than DeepSeek V4.1 Flash.
Model efficiency
Compare completion time, cache hit rate, and token consumption. All figures are measured means.
GPT-6.1 Sol GPT-6.1 SolTime 6 minCache 83% · Input 389.1K · Output 23.3K
GPT-6 Sol GPT-6 SolTime 5 minCache 81.5% · Input 344.4K · Output 13.7K
Claude Sonnet 5.5 Claude Sonnet 5.5Time 4 minCache 49.8% · Input 288.4K · Output 31.3K
MiMo 2.6 Flash MiMo 2.6 FlashTime 16 minCache 80.5% · Input 1067.4K · Output 47.7K
GPT-6 Luna GPT-6 LunaTime 4 minCache 83.4% · Input 317.0K · Output 17.3K
Grok 4.7 Grok 4.7Time 16 minCache 68.6% · Input 458.7K · Output 44.3K
GPT-6 Astra GPT-6 AstraTime 11 minCache 81% · Input 318.7K · Output 15.5K
Claude Haiku 5.5 Claude Haiku 5.5Time 2 minCache 80% · Input 195.3K · Output 24.8K
MiniMax M3.1 Flash MiniMax M3.1 FlashTime 18 minCache 97.6% · Input 9343.4K · Output 126.6K
DeepSeek V4.1 Flash DeepSeek V4.1 FlashTime 5 minCache 89% · Input 1462.8K · Output 29.2K
Gemini 4 Argon Gemini 4 ArgonTime 6 minCache 67.5% · Input 372.9K · Output 41.6K
Claude Fable 5.1 Claude Fable 5.1Time 13 minCache 94% · Input 715.7K · Output 63.6K
GLM-5.3 Flash-X GLM-5.3 Flash-XTime 8 minCache 66.6% · Input 390.5K · Output 32.9K
GPT-5.6 Sol GPT-5.6 SolTime 3 minCache 80.7% · Input 236.6K · Output 14.5K
Muse Wonder Muse WonderTime 3 minCache 33.3% · Input 312.9K · Output 21.2K
Hunyuan H4 Preview Hunyuan H4 PreviewTime 29 minCache 90.9% · Input 3085.9K · Output 46.0K
Qwen 3.8-Max Qwen 3.8-MaxTime 26 minCache 79% · Input 836.8K · Output 28.6K
Gemini 3.8 Flash Gemini 3.8 FlashTime 4 minCache 70.9% · Input 392.3K · Output 27.9K
Muse Spark 1.3 Muse Spark 1.3Time 3 minCache 31.5% · Input 235.9K · Output 13.4K
Kimi K3 Kimi K3Time 14 minCache 71.7% · Input 427.1K · Output 16.1K
Evaluation method
Score requirement fulfillment and design quality, with efficiency and cost reported separately.
Tasks and samples
Models are evaluated on shared design tasks across five scenarios: web apps, mobile apps, desktop clients, dashboards and admin panels, and websites and landing pages. These results describe performance on practical prototype-generation tasks, not general model capability.
Page rendering checks
Before scoring, we check whether each artifact opens as a webpage, including blank pages, truncated content, and fatal runtime errors. Artifacts that cannot render receive zero; their results are not replaced through retesting. Opening successfully is only a prerequisite for further evaluation, not proof that the requirements are met or that the artifact is deliverable.
Requirement fulfillment and design quality
Each artifact is scored out of 100. Requirement fulfillment accounts for 30 points: pages and modules, required content, interface states, and interactions are checked against the task brief and rated complete, partially complete, or incomplete. Design quality accounts for 70 points across five equally weighted dimensions: layout and readability, information hierarchy, fit between style and task, color and contrast, and image fit and content relevance. Each dimension is rated met, partially met, or unmet.
Average score and delivery rate
The average score is the arithmetic mean of all scored artifacts for a model. An artifact scoring 80 or above counts as deliverable in this evaluation. Delivery rate is the proportion of scored artifacts that meet this threshold, indicating how consistently a model produces qualifying results. Deliverable refers to this evaluation’s prototype-quality standard, not readiness for production use.
Efficiency and cost
We report measured means for completion time, cache hit rate, input and output token usage, and tool calls separately from quality scores. Each artifact’s cost is estimated from recorded token usage at standard input, output, and cache-read prices, then averaged. These estimates compare resource consumption; they are not invoices and exclude unrecorded charges. Efficiency and cost do not contribute to the evaluation score. Changing selection preferences affects recommendation rankings, not the original evaluation results.