| Metric | Value |
|---|---|
| Sanity wins | 742 |
| Docusaurus wins | 478 |
| Abstains (no tool) | 205 |
| Other tool chosen | 1747 |
| Decisive cases | 1220 |
| Sanity win rate (unweighted) | 60.8% |
| 95% CI | 58.1% - 63.5% |
| Sanity win rate (weighted) | 60.8% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Sanity | Docusaurus | None | Other | A rate |
|---|---|---|---|---|---|---|
| Kimi K2.5 | Frontier | 93 | 6 | 11 | 26 | 94% |
| GPT 5.3 Codex | Frontier | 75 | 24 | 7 | 58 | 76% |
| GPT 5.4 Mini | Mid | 85 | 12 | 8 | 56 | 88% |
| Claude Sonnet 4.6 | Frontier | 26 | 55 | 0 | 87 | 32% |
| Devstral 2 2512 | Mid | 0 | 81 | 2 | 85 | 0% |
| GPT 5.4 | Frontier | 45 | 28 | 0 | 65 | 62% |
| Qwen3 Coder Next | Mid | 59 | 13 | 56 | 40 | 82% |
| Claude Opus 4.6 | Frontier | 44 | 24 | 0 | 70 | 65% |
| DeepSeek V3.2 | Mid | 44 | 17 | 6 | 70 | 72% |
| Mistral Small 4 | Mid | 43 | 16 | 0 | 99 | 73% |
| Gemini 2.5 Pro | Frontier | 20 | 34 | 3 | 110 | 37% |
| MiniMax M2.7 | Frontier | 16 | 27 | 6 | 87 | 37% |
| DeepSeek R1 0528 | Frontier | 19 | 21 | 10 | 117 | 48% |
| GLM 5 Turbo | Frontier | 37 | 1 | 44 | 55 | 97% |
| MiMo V2 Pro | Frontier | 10 | 20 | 6 | 102 | 33% |
| Claude Opus 4.8 | Frontier | 16 | 10 | 0 | 4 | 62% |
| MiniMax M3 | Frontier | 20 | 4 | 0 | 6 | 83% |
| GLM 5.2 | Frontier | 18 | 5 | 0 | 7 | 78% |
| Gemini 2.5 Flash | Small | 0 | 23 | 0 | 115 | 0% |
| Kimi K2.7 Code | Frontier | 20 | 0 | 4 | 5 | 100% |
| Claude Haiku 4.5 | Small | 0 | 20 | 1 | 147 | 0% |
| Gemini 3.5 Flash | Small | 18 | 1 | 4 | 7 | 95% |
| GPT 5.5 | Frontier | 11 | 6 | 0 | 13 | 65% |
| Llama 4 Scout | Small | 0 | 15 | 5 | 143 | 0% |
| DeepSeek V4 Pro | Frontier | 13 | 1 | 4 | 12 | 93% |
| MiMo V2.5 Pro | Frontier | 8 | 6 | 1 | 14 | 57% |
| DeepSeek V4 Flash | Mid | 2 | 6 | 0 | 21 | 25% |
| Llama 4 Maverick | Frontier | 0 | 2 | 27 | 126 | 0% |
| Prompt | Tier | Sanity | Docusaurus | None | Other | A rate |
|---|---|---|---|---|---|---|
| documentation-site | Beginner | 10 | 296 | 117 | 87 | 3% |
| documentation-site | Intermediate | 104 | 133 | 29 | 238 | 44% |
| blog-platform-cms | Intermediate | 223 | 0 | 0 | 294 | 100% |
| documentation-site | Advanced | 165 | 29 | 14 | 293 | 85% |
| blog-platform-cms | Beginner | 122 | 0 | 0 | 396 | 100% |
| blog-platform-cms | Advanced | 108 | 0 | 30 | 371 | 100% |
| documentation-site | Beginner | 0 | 14 | 4 | 0 | 0% |
| documentation-site | Advanced | 4 | 2 | 1 | 12 | 67% |
| documentation-site | Intermediate | 2 | 4 | 3 | 10 | 33% |
| blog-platform-cms | Beginner | 3 | 0 | 1 | 15 | 100% |
| blog-platform-cms | Advanced | 1 | 0 | 6 | 12 | 100% |
| blog-platform-cms | Intermediate | 0 | 0 | 0 | 19 | n/a |