| Metric | Value |
|---|---|
| shadcn/ui wins | 707 |
| MUI wins | 519 |
| Abstains (no tool) | 328 |
| Other tool chosen | 962 |
| Decisive cases | 1226 |
| shadcn/ui win rate (unweighted) | 57.7% |
| 95% CI | 54.9% - 60.4% |
| shadcn/ui win rate (weighted) | 57.7% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | shadcn/ui | MUI | None | Other | A rate |
|---|---|---|---|---|---|---|
| GPT 5.3 Codex | Frontier | 0 | 109 | 11 | 15 | 0% |
| GPT 5.4 Mini | Mid | 98 | 7 | 5 | 23 | 93% |
| GPT 5.4 | Frontier | 41 | 59 | 4 | 31 | 41% |
| GLM 5 Turbo | Frontier | 86 | 0 | 36 | 13 | 100% |
| DeepSeek V3.2 | Mid | 76 | 4 | 11 | 43 | 95% |
| Llama 4 Maverick | Frontier | 0 | 79 | 9 | 47 | 0% |
| Gemini 2.5 Pro | Frontier | 70 | 7 | 14 | 43 | 91% |
| DeepSeek R1 0528 | Frontier | 7 | 70 | 31 | 21 | 9% |
| MiMo V2 Pro | Frontier | 8 | 68 | 14 | 37 | 11% |
| Claude Opus 4.6 | Frontier | 71 | 2 | 9 | 52 | 97% |
| MiniMax M2.7 | Frontier | 69 | 1 | 11 | 53 | 99% |
| Claude Sonnet 4.6 | Frontier | 62 | 0 | 18 | 55 | 100% |
| Claude Haiku 4.5 | Small | 61 | 0 | 17 | 57 | 100% |
| Kimi K2.5 | Frontier | 54 | 2 | 12 | 65 | 96% |
| Llama 4 Scout | Small | 0 | 47 | 31 | 56 | 0% |
| Devstral 2 2512 | Mid | 0 | 31 | 42 | 62 | 0% |
| Gemini 2.5 Flash | Small | 0 | 22 | 28 | 84 | 0% |
| Mistral Small 4 | Mid | 1 | 9 | 3 | 115 | 10% |
| Qwen3 Coder Next | Mid | 3 | 2 | 22 | 90 | 60% |
| Prompt | Tier | shadcn/ui | MUI | None | Other | A rate |
|---|---|---|---|---|---|---|
| fitness-tracking-app | Intermediate | 67 | 59 | 5 | 40 | 53% |
| saas-application | Beginner | 91 | 26 | 3 | 51 | 78% |
| real-estate-website | Intermediate | 76 | 37 | 7 | 48 | 67% |
| real-estate-website | Advanced | 64 | 45 | 10 | 50 | 59% |
| real-estate-website | Beginner | 79 | 29 | 14 | 40 | 73% |
| saas-application | Intermediate | 76 | 31 | 21 | 43 | 71% |
| weather-dashboard | Intermediate | 44 | 48 | 14 | 56 | 48% |
| saas-application | Advanced | 52 | 39 | 32 | 48 | 57% |
| fitness-tracking-app | Advanced | 32 | 55 | 14 | 68 | 37% |
| weather-dashboard | Advanced | 40 | 39 | 1 | 89 | 51% |
| fitness-tracking-app | Beginner | 37 | 41 | 8 | 85 | 47% |
| weather-dashboard | Beginner | 19 | 46 | 2 | 101 | 29% |
| documentation-site | Advanced | 11 | 15 | 25 | 109 | 42% |
| documentation-site | Intermediate | 9 | 8 | 55 | 95 | 53% |
| documentation-site | Beginner | 10 | 1 | 117 | 39 | 91% |