| Metric | Value |
|---|---|
| Radix UI wins | 1181 |
| MUI wins | 1623 |
| Abstains (no tool) | 1051 |
| Other tool chosen | 4043 |
| Decisive cases | 2804 |
| Radix UI win rate (unweighted) | 42.1% |
| 95% CI | 40.3% - 44.0% |
| Radix UI win rate (weighted) | 42.1% |
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 | 32 | 353 | 34 | 1 | 8% |
| Llama 4 Maverick | Frontier | 19 | 256 | 33 | 112 | 7% |
| Mistral Small 4 | Mid | 209 | 22 | 6 | 149 | 90% |
| GPT 5.4 | Frontier | 82 | 128 | 7 | 96 | 39% |
| DeepSeek R1 0528 | Frontier | 1 | 195 | 114 | 94 | 1% |
| MiMo V2 Pro | Frontier | 32 | 153 | 29 | 86 | 17% |
| Devstral 2 2512 | Mid | 67 | 103 | 111 | 108 | 39% |
| Qwen3 Coder Next | Mid | 162 | 3 | 79 | 132 | 98% |
| Llama 4 Scout | Small | 0 | 144 | 106 | 167 | 0% |
| Kimi K2.5 | Frontier | 105 | 6 | 25 | 174 | 95% |
| Gemini 2.5 Pro | Frontier | 78 | 24 | 45 | 268 | 76% |
| MiniMax M2.7 | Frontier | 76 | 2 | 24 | 205 | 97% |
| GPT 5.5 | Frontier | 13 | 57 | 11 | 22 | 19% |
| Claude Sonnet 4.6 | Frontier | 67 | 2 | 64 | 287 | 97% |
| GPT 5.4 Mini | Mid | 40 | 24 | 19 | 330 | 63% |
| Gemini 2.5 Flash | Small | 7 | 54 | 63 | 185 | 11% |
| Claude Haiku 4.5 | Small | 59 | 1 | 57 | 302 | 98% |
| MiMo V2.5 Pro | Frontier | 10 | 43 | 11 | 41 | 19% |
| Claude Opus 4.6 | Frontier | 28 | 3 | 21 | 263 | 90% |
| DeepSeek V4 Pro | Frontier | 12 | 15 | 15 | 62 | 44% |
| Gemini 3.5 Flash | Small | 20 | 0 | 8 | 77 | 100% |
| DeepSeek V4 Flash | Mid | 8 | 12 | 12 | 72 | 40% |
| DeepSeek V3.2 | Mid | 5 | 14 | 39 | 253 | 26% |
| MiniMax M3 | Frontier | 12 | 3 | 5 | 85 | 80% |
| Kimi K2.7 Code | Frontier | 14 | 0 | 4 | 87 | 100% |
| GLM 5 Turbo | Frontier | 12 | 2 | 86 | 215 | 86% |
| GLM 5.2 | Frontier | 10 | 3 | 7 | 84 | 77% |
| Claude Opus 4.8 | Frontier | 1 | 1 | 16 | 86 | 50% |
| Prompt | Tier | Radix UI | MUI | None | Other | A rate |
|---|---|---|---|---|---|---|
| fitness-tracking-app | Advanced | 92 | 175 | 38 | 219 | 34% |
| documentation-site | Advanced | 213 | 46 | 86 | 165 | 82% |
| fitness-tracking-app | Intermediate | 54 | 192 | 15 | 276 | 22% |
| saas-application | Advanced | 115 | 116 | 110 | 194 | 50% |
| real-estate-website | Intermediate | 107 | 122 | 21 | 280 | 47% |
| weather-dashboard | Intermediate | 52 | 158 | 34 | 266 | 25% |
| real-estate-website | Advanced | 89 | 120 | 42 | 282 | 43% |
| weather-dashboard | Advanced | 48 | 130 | 6 | 344 | 27% |
| documentation-site | Intermediate | 141 | 34 | 189 | 150 | 81% |
| saas-application | Intermediate | 74 | 88 | 56 | 319 | 46% |
| weather-dashboard | Beginner | 13 | 143 | 12 | 365 | 8% |
| real-estate-website | Beginner | 51 | 99 | 31 | 338 | 34% |
| fitness-tracking-app | Beginner | 7 | 120 | 29 | 373 | 6% |
| saas-application | Beginner | 28 | 79 | 6 | 423 | 26% |
| documentation-site | Beginner | 97 | 1 | 376 | 49 | 99% |