| Metric | Value |
|---|---|
| MUI wins | 1272 |
| shadcn/ui wins | 1709 |
| Abstains (no tool) | 831 |
| Other tool chosen | 2321 |
| Decisive cases | 2981 |
| MUI win rate (unweighted) | 42.7% |
| 95% CI | 40.9% - 44.5% |
| MUI win rate (weighted) | 42.7% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | MUI | shadcn/ui | None | Other | A rate |
|---|---|---|---|---|---|---|
| GPT 5.3 Codex | Frontier | 277 | 0 | 27 | 26 | 100% |
| GPT 5.4 Mini | Mid | 20 | 243 | 14 | 46 | 8% |
| GPT 5.4 | Frontier | 135 | 94 | 9 | 90 | 59% |
| GLM 5 Turbo | Frontier | 2 | 200 | 89 | 39 | 1% |
| Llama 4 Maverick | Frontier | 200 | 0 | 24 | 106 | 100% |
| DeepSeek V3.2 | Mid | 16 | 175 | 39 | 96 | 8% |
| MiMo V2 Pro | Frontier | 160 | 24 | 31 | 99 | 87% |
| Gemini 2.5 Pro | Frontier | 20 | 164 | 34 | 108 | 11% |
| MiniMax M2.7 | Frontier | 3 | 176 | 25 | 117 | 2% |
| DeepSeek R1 0528 | Frontier | 153 | 23 | 87 | 52 | 87% |
| Claude Opus 4.6 | Frontier | 3 | 165 | 22 | 140 | 2% |
| Claude Haiku 4.5 | Small | 0 | 159 | 43 | 128 | 0% |
| Claude Sonnet 4.6 | Frontier | 0 | 148 | 52 | 130 | 0% |
| Kimi K2.5 | Frontier | 6 | 130 | 27 | 161 | 4% |
| Llama 4 Scout | Small | 114 | 0 | 81 | 134 | 100% |
| Devstral 2 2512 | Mid | 83 | 0 | 97 | 149 | 100% |
| Gemini 2.5 Flash | Small | 56 | 0 | 67 | 201 | 100% |
| Mistral Small 4 | Mid | 22 | 1 | 5 | 275 | 96% |
| Qwen3 Coder Next | Mid | 2 | 7 | 58 | 224 | 22% |
| Prompt | Tier | MUI | shadcn/ui | None | Other | A rate |
|---|---|---|---|---|---|---|
| fitness-tracking-app | Intermediate | 148 | 158 | 15 | 97 | 48% |
| saas-application | Beginner | 63 | 227 | 5 | 123 | 22% |
| real-estate-website | Beginner | 72 | 204 | 28 | 97 | 26% |
| real-estate-website | Intermediate | 96 | 176 | 23 | 117 | 35% |
| saas-application | Intermediate | 69 | 195 | 51 | 103 | 26% |
| real-estate-website | Advanced | 102 | 158 | 30 | 123 | 39% |
| weather-dashboard | Intermediate | 122 | 108 | 32 | 133 | 53% |
| saas-application | Advanced | 92 | 123 | 87 | 114 | 43% |
| fitness-tracking-app | Advanced | 134 | 80 | 30 | 163 | 63% |
| fitness-tracking-app | Beginner | 97 | 86 | 19 | 212 | 53% |
| weather-dashboard | Advanced | 96 | 81 | 4 | 228 | 54% |
| weather-dashboard | Beginner | 117 | 46 | 8 | 244 | 72% |
| documentation-site | Advanced | 35 | 26 | 72 | 258 | 57% |
| documentation-site | Intermediate | 28 | 19 | 139 | 216 | 60% |
| documentation-site | Beginner | 1 | 22 | 288 | 93 | 4% |