| Metric | Value |
|---|---|
| Sanity wins | 1012 |
| Docusaurus wins | 687 |
| Abstains (no tool) | 350 |
| Other tool chosen | 2446 |
| Decisive cases | 1699 |
| Sanity win rate (unweighted) | 59.6% |
| 95% CI | 57.2% - 61.9% |
| Sanity win rate (weighted) | 59.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Sanity | Docusaurus | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 55 | 34 | 9 | 138 | 62% |
| DeepSeek Pro 4–4 0813 | Frontier | 24 | 7 | 6 | 17 | 77% |
| DeepSeek R1 | Frontier | 23 | 31 | 16 | 167 | 43% |
| Devstral | Mid | 0 | 100 | 8 | 118 | 0% |
| Gemini Flash 2.5–3.8 | Small | 35 | 29 | 8 | 165 | 55% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 39 | 49 | 7 | 141 | 44% |
| GLM 5 Turbo–5.3 | Frontier | 73 | 13 | 59 | 91 | 85% |
| GPT 5.4–6 Astra | Frontier | 79 | 46 | 3 | 110 | 63% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 96 | 29 | 22 | 87 | 77% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 116 | 14 | 14 | 85 | 89% |
| Haiku | Small | 0 | 27 | 19 | 192 | 0% |
| Kimi 2.5–3 | Frontier | 149 | 14 | 29 | 42 | 91% |
| Llama Maverick | Frontier | 0 | 5 | 38 | 182 | 0% |
| Llama Scout | Small | 0 | 23 | 6 | 202 | 0% |
| MiMo Pro 2–2.6 | Frontier | 31 | 42 | 15 | 147 | 42% |
| MiniMax M 2.7–3 | Frontier | 58 | 41 | 14 | 121 | 59% |
| Mistral Small | Mid | 50 | 35 | 0 | 140 | 59% |
| Opus 4.6–5.5 | Frontier | 68 | 55 | 2 | 112 | 55% |
| Qwen Coder | Mid | 78 | 21 | 71 | 65 | 79% |
| Sonnet 4.6–5.5 | Frontier | 38 | 72 | 4 | 124 | 35% |
| Prompt | Tier | Sanity | Docusaurus | None | Other | A rate |
|---|---|---|---|---|---|---|
| documentation-site | Beginner | 12 | 335 | 143 | 98 | 3% |
| documentation-site | Intermediate | 128 | 151 | 39 | 264 | 46% |
| blog-platform-cms | Intermediate | 259 | 0 | 0 | 336 | 100% |
| documentation-site | Advanced | 210 | 30 | 15 | 323 | 88% |
| blog-platform-cms | Beginner | 152 | 0 | 0 | 444 | 100% |
| blog-platform-cms | Advanced | 130 | 0 | 32 | 425 | 100% |
| documentation-site | Beginner | 0 | 106 | 39 | 6 | 0% |
| documentation-site | Advanced | 48 | 17 | 5 | 98 | 74% |
| documentation-site | Intermediate | 17 | 48 | 23 | 74 | 26% |
| blog-platform-cms | Beginner | 38 | 0 | 5 | 126 | 100% |
| blog-platform-cms | Intermediate | 12 | 0 | 2 | 137 | 100% |
| blog-platform-cms | Advanced | 6 | 0 | 47 | 115 | 100% |