| Metric | Value |
|---|---|
| Radix UI wins | 1186 |
| MUI wins | 1623 |
| Abstains (no tool) | 1059 |
| Other tool chosen | 4025 |
| Decisive cases | 2809 |
| Radix UI win rate (unweighted) | 42.2% |
| 95% CI | 40.4% - 44.1% |
| Radix UI win rate (weighted) | 42.2% |
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 | 30 | 354 | 35 | 1 | 8% |
| Llama 4 Maverick | Frontier | 21 | 253 | 33 | 113 | 8% |
| Mistral Small 4 | Mid | 210 | 23 | 6 | 147 | 90% |
| GPT 5.4 | Frontier | 83 | 135 | 9 | 101 | 38% |
| DeepSeek R1 0528 | Frontier | 3 | 192 | 113 | 93 | 2% |
| MiMo V2 Pro | Frontier | 33 | 160 | 31 | 90 | 17% |
| Devstral 2 2512 | Mid | 69 | 105 | 117 | 113 | 40% |
| Qwen3 Coder Next | Mid | 161 | 3 | 80 | 131 | 98% |
| Llama 4 Scout | Small | 0 | 144 | 107 | 166 | 0% |
| Kimi K2.5 | Frontier | 108 | 6 | 27 | 183 | 95% |
| Gemini 2.5 Pro | Frontier | 79 | 24 | 44 | 268 | 77% |
| MiniMax M2.7 | Frontier | 80 | 3 | 25 | 213 | 96% |
| Claude Sonnet 4.6 | Frontier | 68 | 2 | 64 | 286 | 97% |
| GPT 5.4 Mini | Mid | 42 | 25 | 18 | 328 | 63% |
| Gemini 2.5 Flash | Small | 7 | 56 | 67 | 194 | 11% |
| Claude Haiku 4.5 | Small | 60 | 1 | 56 | 303 | 98% |
| GPT 5.5 | Frontier | 11 | 50 | 9 | 19 | 18% |
| MiMo V2.5 Pro | Frontier | 8 | 38 | 9 | 35 | 17% |
| Claude Opus 4.6 | Frontier | 30 | 3 | 22 | 275 | 91% |
| DeepSeek V4 Pro | Frontier | 9 | 13 | 13 | 54 | 41% |
| DeepSeek V3.2 | Mid | 5 | 16 | 39 | 266 | 24% |
| Gemini 3.5 Flash | Small | 16 | 0 | 7 | 67 | 100% |
| GLM 5 Turbo | Frontier | 14 | 2 | 89 | 225 | 88% |
| MiniMax M3 | Frontier | 12 | 3 | 4 | 71 | 80% |
| DeepSeek V4 Flash | Mid | 6 | 9 | 11 | 63 | 40% |
| Kimi K2.7 Code | Frontier | 11 | 0 | 4 | 75 | 100% |
| GLM 5.2 | Frontier | 9 | 2 | 6 | 72 | 82% |
| Claude Opus 4.8 | Frontier | 1 | 1 | 14 | 73 | 50% |
| Prompt | Tier | Radix UI | MUI | None | Other | A rate |
|---|---|---|---|---|---|---|
| fitness-tracking-app | Advanced | 94 | 175 | 41 | 214 | 35% |
| documentation-site | Advanced | 210 | 45 | 87 | 166 | 82% |
| fitness-tracking-app | Intermediate | 56 | 192 | 15 | 274 | 23% |
| saas-application | Advanced | 116 | 119 | 110 | 190 | 49% |
| real-estate-website | Intermediate | 109 | 120 | 23 | 278 | 48% |
| weather-dashboard | Intermediate | 50 | 161 | 33 | 265 | 24% |
| real-estate-website | Advanced | 90 | 119 | 42 | 281 | 43% |
| documentation-site | Intermediate | 143 | 35 | 187 | 150 | 80% |
| weather-dashboard | Advanced | 49 | 127 | 6 | 345 | 28% |
| saas-application | Intermediate | 76 | 89 | 58 | 314 | 46% |
| weather-dashboard | Beginner | 12 | 145 | 11 | 365 | 8% |
| real-estate-website | Beginner | 49 | 96 | 32 | 340 | 34% |
| fitness-tracking-app | Beginner | 7 | 122 | 30 | 371 | 5% |
| saas-application | Beginner | 30 | 77 | 6 | 423 | 28% |
| documentation-site | Beginner | 95 | 1 | 378 | 49 | 99% |