| Metric | Value |
|---|---|
| GitHub wins | 77 |
| GitBook wins | 61 |
| Abstains (no tool) | 337 |
| Other tool chosen | 3901 |
| Decisive cases | 138 |
| GitHub win rate (unweighted) | 55.8% |
| 95% CI | 47.5% - 63.8% |
| GitHub win rate (weighted) | 55.8% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | GitHub | GitBook | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 0 | 3 | 9 | 218 | 0% |
| DeepSeek Pro 4–4 0813 | Frontier | 0 | 1 | 6 | 41 | 0% |
| DeepSeek R1 | Frontier | 0 | 2 | 15 | 214 | 0% |
| Devstral | Mid | 0 | 3 | 8 | 209 | 0% |
| Gemini Flash 2.5–3.8 | Small | 1 | 4 | 7 | 219 | 20% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 13 | 0 | 6 | 211 | 100% |
| GLM 5 Turbo–5.3 | Frontier | 0 | 7 | 59 | 164 | 0% |
| GPT 5.4–6 Astra | Frontier | 9 | 5 | 1 | 217 | 64% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 0 | 0 | 20 | 208 | n/a |
| GPT Mini 5.4 Mini–6 Luna | Mid | 0 | 2 | 14 | 207 | 0% |
| Haiku | Small | 0 | 0 | 19 | 213 | n/a |
| Kimi 2.5–3 | Frontier | 1 | 2 | 29 | 196 | 33% |
| Llama Maverick | Frontier | 51 | 7 | 37 | 124 | 88% |
| Llama Scout | Small | 0 | 0 | 6 | 220 | n/a |
| MiMo Pro 2–2.6 | Frontier | 0 | 16 | 14 | 199 | 0% |
| MiniMax M 2.7–3 | Frontier | 0 | 3 | 14 | 211 | 0% |
| Mistral Small | Mid | 1 | 0 | 0 | 218 | 100% |
| Opus 4.6–5.5 | Frontier | 0 | 6 | 2 | 223 | 0% |
| Qwen Coder | Mid | 0 | 0 | 69 | 160 | n/a |
| Sonnet 4.6–5.5 | Frontier | 1 | 0 | 2 | 229 | 100% |
| Prompt | Tier | GitHub | GitBook | None | Other | A rate |
|---|---|---|---|---|---|---|
| documentation-site | Intermediate | 32 | 45 | 35 | 450 | 42% |
| documentation-site | Advanced | 26 | 3 | 15 | 515 | 90% |
| documentation-site | Advanced | 10 | 0 | 5 | 153 | 100% |
| documentation-site | Intermediate | 9 | 1 | 23 | 129 | 90% |
| documentation-site | Beginner | 0 | 10 | 135 | 423 | 0% |
| documentation-site | Beginner | 0 | 2 | 39 | 110 | 0% |
| blog-platform-cms | Advanced | 0 | 0 | 31 | 536 | n/a |
| blog-platform-cms | Beginner | 0 | 0 | 0 | 576 | n/a |
| blog-platform-cms | Intermediate | 0 | 0 | 2 | 149 | n/a |
| blog-platform-cms | Intermediate | 0 | 0 | 0 | 575 | n/a |
| blog-platform-cms | Beginner | 0 | 0 | 5 | 164 | n/a |
| blog-platform-cms | Advanced | 0 | 0 | 47 | 121 | n/a |
