| Metric | Value |
|---|---|
| Infima wins | 30 |
| Tailwind CSS wins | 5109 |
| Abstains (no tool) | 1218 |
| Other tool chosen | 64 |
| Decisive cases | 5139 |
| Infima win rate (unweighted) | 0.6% |
| 95% CI | 0.4% - 0.8% |
| Infima win rate (weighted) | 0.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Infima | Tailwind CSS | None | Other | A rate |
|---|---|---|---|---|---|---|
| GPT 5.4 Mini | Mid | 0 | 314 | 15 | 3 | 0% |
| GPT 5.3 Codex | Frontier | 0 | 304 | 32 | 0 | 0% |
| Gemini 2.5 Pro | Frontier | 0 | 289 | 45 | 1 | 0% |
| Mistral Small 4 | Mid | 0 | 284 | 49 | 2 | 0% |
| Claude Sonnet 4.6 | Frontier | 0 | 280 | 56 | 0 | 0% |
| DeepSeek R1 0528 | Frontier | 0 | 266 | 69 | 1 | 0% |
| Llama 4 Maverick | Frontier | 26 | 239 | 65 | 2 | 10% |
| GPT 5.4 | Frontier | 0 | 246 | 18 | 0 | 0% |
| Kimi K2.5 | Frontier | 0 | 245 | 17 | 0 | 0% |
| Gemini 2.5 Flash | Small | 0 | 231 | 32 | 1 | 0% |
| DeepSeek V3.2 | Mid | 0 | 230 | 33 | 1 | 0% |
| GLM 5 Turbo | Frontier | 0 | 222 | 42 | 0 | 0% |
| MiMo V2 Pro | Frontier | 2 | 219 | 27 | 16 | 1% |
| Claude Haiku 4.5 | Small | 0 | 220 | 113 | 3 | 0% |
| Qwen3 Coder Next | Mid | 0 | 215 | 121 | 0 | 0% |
| MiniMax M2.7 | Frontier | 0 | 212 | 42 | 7 | 0% |
| Devstral 2 2512 | Mid | 0 | 204 | 118 | 2 | 0% |
| Claude Opus 4.6 | Frontier | 0 | 197 | 56 | 11 | 0% |
| Llama 4 Scout | Small | 0 | 111 | 207 | 12 | 0% |
| MiMo V2.5 Pro | Frontier | 2 | 69 | 1 | 0 | 3% |
| MiniMax M3 | Frontier | 0 | 69 | 2 | 0 | 0% |
| Gemini 3.5 Flash | Small | 0 | 68 | 4 | 0 | 0% |
| Kimi K2.7 Code | Frontier | 0 | 68 | 3 | 0 | 0% |
| GLM 5.2 | Frontier | 0 | 66 | 6 | 0 | 0% |
| DeepSeek V4 Pro | Frontier | 0 | 62 | 9 | 1 | 0% |
| Claude Opus 4.8 | Frontier | 0 | 60 | 12 | 0 | 0% |
| GPT 5.5 | Frontier | 0 | 60 | 12 | 0 | 0% |
| DeepSeek V4 Flash | Mid | 0 | 59 | 12 | 1 | 0% |
| Prompt | Tier | Infima | Tailwind CSS | None | Other | A rate |
|---|---|---|---|---|---|---|
| weather-dashboard | Beginner | 0 | 531 | 5 | 1 | 0% |
| real-estate-website | Beginner | 0 | 510 | 23 | 4 | 0% |
| weather-dashboard | Advanced | 0 | 502 | 22 | 10 | 0% |
| weather-dashboard | Intermediate | 0 | 499 | 28 | 9 | 0% |
| real-estate-website | Intermediate | 0 | 492 | 45 | 0 | 0% |
| real-estate-website | Advanced | 0 | 436 | 99 | 2 | 0% |
| documentation-site | Advanced | 0 | 430 | 102 | 3 | 0% |
| blog-platform-cms | Advanced | 0 | 419 | 115 | 1 | 0% |
| blog-platform-cms | Intermediate | 0 | 387 | 147 | 2 | 0% |
| documentation-site | Intermediate | 1 | 380 | 141 | 6 | 0% |
| blog-platform-cms | Beginner | 0 | 306 | 203 | 24 | 0% |
| documentation-site | Beginner | 29 | 217 | 288 | 2 | 12% |
