| Metric | Value |
|---|---|
| MUI wins | 1623 |
| shadcn/ui wins | 2370 |
| Abstains (no tool) | 1051 |
| Other tool chosen | 2854 |
| Decisive cases | 3993 |
| MUI win rate (unweighted) | 40.6% |
| 95% CI | 39.1% - 42.2% |
| MUI win rate (weighted) | 40.6% |
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 | 353 | 0 | 34 | 33 | 100% |
| GPT 5.4 Mini | Mid | 24 | 309 | 19 | 61 | 7% |
| Llama 4 Maverick | Frontier | 256 | 0 | 33 | 131 | 100% |
| DeepSeek R1 0528 | Frontier | 195 | 34 | 114 | 61 | 85% |
| Gemini 2.5 Pro | Frontier | 24 | 205 | 45 | 141 | 10% |
| GPT 5.4 | Frontier | 128 | 89 | 7 | 89 | 59% |
| Claude Haiku 4.5 | Small | 1 | 204 | 57 | 157 | 0% |
| GLM 5 Turbo | Frontier | 2 | 191 | 86 | 36 | 1% |
| Claude Sonnet 4.6 | Frontier | 2 | 190 | 64 | 164 | 1% |
| DeepSeek V3.2 | Mid | 14 | 167 | 39 | 91 | 8% |
| MiMo V2 Pro | Frontier | 153 | 22 | 29 | 96 | 87% |
| MiniMax M2.7 | Frontier | 2 | 170 | 24 | 111 | 1% |
| Claude Opus 4.6 | Frontier | 3 | 156 | 21 | 135 | 2% |
| Llama 4 Scout | Small | 144 | 0 | 106 | 167 | 100% |
| Kimi K2.5 | Frontier | 6 | 123 | 25 | 156 | 5% |
| Devstral 2 2512 | Mid | 103 | 0 | 111 | 175 | 100% |
| GLM 5.2 | Frontier | 3 | 83 | 7 | 11 | 3% |
| MiniMax M3 | Frontier | 3 | 79 | 5 | 18 | 4% |
| Kimi K2.7 Code | Frontier | 0 | 80 | 4 | 21 | 0% |
| GPT 5.5 | Frontier | 57 | 15 | 11 | 20 | 79% |
| DeepSeek V4 Flash | Mid | 12 | 55 | 12 | 25 | 18% |
| MiMo V2.5 Pro | Frontier | 43 | 21 | 11 | 30 | 67% |
| Gemini 3.5 Flash | Small | 0 | 64 | 8 | 33 | 0% |
| Claude Opus 4.8 | Frontier | 1 | 60 | 16 | 27 | 2% |
| DeepSeek V4 Pro | Frontier | 15 | 44 | 15 | 30 | 25% |
| Gemini 2.5 Flash | Small | 54 | 0 | 63 | 192 | 100% |
| Mistral Small 4 | Mid | 22 | 1 | 6 | 357 | 96% |
| Qwen3 Coder Next | Mid | 3 | 8 | 79 | 286 | 27% |
| Prompt | Tier | MUI | shadcn/ui | None | Other | A rate |
|---|---|---|---|---|---|---|
| fitness-tracking-app | Intermediate | 192 | 210 | 15 | 120 | 48% |
| saas-application | Beginner | 79 | 309 | 6 | 142 | 20% |
| real-estate-website | Beginner | 99 | 274 | 31 | 115 | 27% |
| real-estate-website | Intermediate | 122 | 245 | 21 | 142 | 33% |
| saas-application | Intermediate | 88 | 274 | 56 | 119 | 24% |
| real-estate-website | Advanced | 120 | 220 | 42 | 151 | 35% |
| weather-dashboard | Intermediate | 158 | 153 | 34 | 165 | 51% |
| saas-application | Advanced | 116 | 173 | 110 | 136 | 40% |
| fitness-tracking-app | Advanced | 175 | 112 | 38 | 199 | 61% |
| weather-dashboard | Advanced | 130 | 114 | 6 | 278 | 53% |
| fitness-tracking-app | Beginner | 120 | 122 | 29 | 258 | 50% |
| weather-dashboard | Beginner | 143 | 74 | 12 | 304 | 66% |
| documentation-site | Advanced | 46 | 36 | 86 | 342 | 56% |
| documentation-site | Intermediate | 34 | 30 | 189 | 261 | 53% |
| documentation-site | Beginner | 1 | 24 | 376 | 122 | 4% |