| Metric | Value |
|---|---|
| Docusaurus wins | 486 |
| Sanity wins | 649 |
| Abstains (no tool) | 234 |
| Other tool chosen | 1781 |
| Decisive cases | 1135 |
| Docusaurus win rate (unweighted) | 42.8% |
| 95% CI | 40.0% - 45.7% |
| Docusaurus win rate (weighted) | 42.8% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Docusaurus | Sanity | None | Other | A rate |
|---|---|---|---|---|---|---|
| Kimi K2.5 | Frontier | 8 | 104 | 17 | 31 | 7% |
| GPT 5.4 Mini | Mid | 11 | 82 | 8 | 61 | 12% |
| GPT 5.3 Codex | Frontier | 23 | 69 | 12 | 61 | 25% |
| GPT 5.4 | Frontier | 33 | 55 | 0 | 74 | 38% |
| Claude Sonnet 4.6 | Frontier | 54 | 26 | 0 | 88 | 68% |
| Devstral 2 2512 | Mid | 78 | 0 | 5 | 85 | 100% |
| Claude Opus 4.6 | Frontier | 32 | 44 | 0 | 86 | 42% |
| Qwen3 Coder Next | Mid | 15 | 56 | 53 | 44 | 21% |
| DeepSeek V3.2 | Mid | 21 | 44 | 7 | 89 | 32% |
| Mistral Small 4 | Mid | 19 | 37 | 0 | 103 | 34% |
| Gemini 2.5 Pro | Frontier | 34 | 21 | 6 | 106 | 62% |
| MiniMax M2.7 | Frontier | 32 | 20 | 10 | 97 | 62% |
| GLM 5 Turbo | Frontier | 2 | 41 | 51 | 66 | 5% |
| MiMo V2 Pro | Frontier | 27 | 11 | 10 | 114 | 71% |
| DeepSeek R1 0528 | Frontier | 22 | 15 | 12 | 118 | 59% |
| Gemini 2.5 Flash | Small | 25 | 0 | 0 | 136 | 100% |
| Claude Haiku 4.5 | Small | 21 | 0 | 8 | 139 | 100% |
| Llama 4 Scout | Small | 16 | 0 | 4 | 143 | 100% |
| Claude Opus 4.8 | Frontier | 2 | 3 | 0 | 1 | 40% |
| MiniMax M3 | Frontier | 1 | 4 | 0 | 1 | 20% |
| GPT 5.5 | Frontier | 2 | 2 | 0 | 2 | 50% |
| GLM 5.2 | Frontier | 1 | 3 | 0 | 2 | 25% |
| Gemini 3.5 Flash | Small | 0 | 4 | 1 | 1 | 0% |
| Kimi K2.7 Code | Frontier | 0 | 4 | 1 | 0 | 0% |
| Llama 4 Maverick | Frontier | 3 | 0 | 28 | 125 | 100% |
| DeepSeek V4 Flash | Mid | 2 | 1 | 0 | 3 | 67% |
| MiMo V2.5 Pro | Frontier | 2 | 1 | 0 | 2 | 67% |
| DeepSeek V4 Pro | Frontier | 0 | 2 | 1 | 3 | 0% |
| Prompt | Tier | Docusaurus | Sanity | None | Other | A rate |
|---|---|---|---|---|---|---|
| documentation-site | Beginner | 250 | 9 | 96 | 76 | 97% |
| documentation-site | Intermediate | 110 | 77 | 26 | 214 | 59% |
| blog-platform-cms | Intermediate | 0 | 182 | 0 | 255 | 0% |
| documentation-site | Advanced | 25 | 129 | 14 | 255 | 16% |
| blog-platform-cms | Beginner | 0 | 96 | 0 | 342 | 0% |
| blog-platform-cms | Advanced | 0 | 88 | 29 | 313 | 0% |
| documentation-site | Beginner | 66 | 0 | 24 | 4 | 100% |
| documentation-site | Intermediate | 27 | 12 | 11 | 41 | 69% |
| documentation-site | Advanced | 8 | 26 | 2 | 59 | 24% |
| blog-platform-cms | Beginner | 0 | 20 | 3 | 72 | 0% |
| blog-platform-cms | Advanced | 0 | 5 | 28 | 62 | 0% |
| blog-platform-cms | Intermediate | 0 | 5 | 1 | 88 | 0% |