| Metric | Value |
|---|---|
| Radix UI wins | 1149 |
| MUI wins | 1551 |
| Abstains (no tool) | 1097 |
| Other tool chosen | 4023 |
| Decisive cases | 2700 |
| Radix UI win rate (unweighted) | 42.6% |
| 95% CI | 40.7% - 44.4% |
| Radix UI win rate (weighted) | 42.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Radix UI | MUI | None | Other | A rate |
|---|---|---|---|---|---|---|
| GPT 5.3 Codex | Frontier | 37 | 346 | 33 | 4 | 10% |
| Llama 4 Maverick | Frontier | 25 | 244 | 31 | 119 | 9% |
| GPT 5.4 | Frontier | 94 | 154 | 11 | 143 | 38% |
| MiMo V2 Pro | Frontier | 42 | 181 | 38 | 121 | 19% |
| Mistral Small 4 | Mid | 193 | 24 | 10 | 158 | 89% |
| DeepSeek R1 0528 | Frontier | 4 | 189 | 113 | 97 | 2% |
| Devstral 2 2512 | Mid | 58 | 100 | 140 | 120 | 37% |
| Qwen3 Coder Next | Mid | 155 | 2 | 77 | 135 | 99% |
| Llama 4 Scout | Small | 0 | 139 | 104 | 175 | 0% |
| Kimi K2.5 | Frontier | 125 | 7 | 32 | 235 | 95% |
| MiniMax M2.7 | Frontier | 98 | 5 | 33 | 259 | 95% |
| Gemini 2.5 Pro | Frontier | 77 | 26 | 45 | 268 | 75% |
| Gemini 2.5 Flash | Small | 8 | 61 | 94 | 234 | 12% |
| Claude Sonnet 4.6 | Frontier | 65 | 1 | 61 | 291 | 98% |
| GPT 5.4 Mini | Mid | 39 | 24 | 18 | 332 | 62% |
| Claude Haiku 4.5 | Small | 54 | 2 | 55 | 309 | 96% |
| Claude Opus 4.6 | Frontier | 36 | 3 | 35 | 331 | 92% |
| DeepSeek V3.2 | Mid | 6 | 20 | 48 | 327 | 23% |
| GLM 5 Turbo | Frontier | 15 | 2 | 106 | 282 | 88% |
| GPT 5.5 | Frontier | 3 | 9 | 2 | 1 | 25% |
| MiMo V2.5 Pro | Frontier | 1 | 5 | 1 | 8 | 17% |
| DeepSeek V4 Flash | Mid | 2 | 3 | 3 | 7 | 40% |
| MiniMax M3 | Frontier | 4 | 0 | 1 | 10 | 100% |
| DeepSeek V4 Pro | Frontier | 2 | 2 | 2 | 9 | 50% |
| Gemini 3.5 Flash | Small | 3 | 0 | 1 | 11 | 100% |
| GLM 5.2 | Frontier | 1 | 2 | 1 | 11 | 33% |
| Kimi K2.7 Code | Frontier | 2 | 0 | 0 | 13 | 100% |
| Claude Opus 4.8 | Frontier | 0 | 0 | 2 | 13 | n/a |
| Prompt | Tier | Radix UI | MUI | None | Other | A rate |
|---|---|---|---|---|---|---|
| fitness-tracking-app | Advanced | 81 | 140 | 32 | 174 | 37% |
| documentation-site | Advanced | 167 | 37 | 74 | 133 | 82% |
| fitness-tracking-app | Intermediate | 47 | 157 | 15 | 219 | 23% |
| saas-application | Advanced | 104 | 96 | 89 | 147 | 52% |
| real-estate-website | Intermediate | 94 | 101 | 23 | 214 | 48% |
| real-estate-website | Advanced | 76 | 103 | 33 | 221 | 42% |
| weather-dashboard | Intermediate | 42 | 127 | 32 | 212 | 25% |
| weather-dashboard | Advanced | 43 | 103 | 4 | 279 | 29% |
| documentation-site | Intermediate | 115 | 29 | 146 | 130 | 80% |
| saas-application | Intermediate | 67 | 73 | 53 | 245 | 48% |
| weather-dashboard | Beginner | 7 | 122 | 9 | 296 | 5% |
| real-estate-website | Beginner | 41 | 76 | 29 | 275 | 35% |
| fitness-tracking-app | Beginner | 6 | 102 | 21 | 305 | 6% |
| saas-application | Beginner | 26 | 66 | 5 | 341 | 28% |
| documentation-site | Beginner | 81 | 1 | 304 | 38 | 99% |
| documentation-site | Advanced | 33 | 9 | 14 | 36 | 79% |
| saas-application | Advanced | 14 | 27 | 19 | 35 | 34% |
| fitness-tracking-app | Advanced | 15 | 21 | 14 | 44 | 42% |
| real-estate-website | Advanced | 8 | 25 | 7 | 54 | 24% |
| fitness-tracking-app | Intermediate | 6 | 27 | 1 | 60 | 18% |
| weather-dashboard | Advanced | 8 | 20 | 1 | 65 | 29% |
| weather-dashboard | Intermediate | 11 | 15 | 13 | 54 | 42% |
| real-estate-website | Intermediate | 13 | 9 | 9 | 62 | 59% |
| saas-application | Intermediate | 11 | 9 | 10 | 65 | 55% |
| documentation-site | Intermediate | 16 | 3 | 40 | 28 | 84% |
| fitness-tracking-app | Beginner | 2 | 17 | 10 | 66 | 11% |
| saas-application | Beginner | 1 | 18 | 0 | 72 | 5% |
| real-estate-website | Beginner | 5 | 8 | 13 | 61 | 38% |
| weather-dashboard | Beginner | 1 | 10 | 3 | 81 | 9% |
| documentation-site | Beginner | 8 | 0 | 74 | 11 | 100% |