| Metric | Value |
|---|---|
| GitBook wins | 52 |
| GitHub wins | 55 |
| Abstains (no tool) | 197 |
| Other tool chosen | 2869 |
| Decisive cases | 107 |
| GitBook win rate (unweighted) | 48.6% |
| 95% CI | 39.3% - 58.0% |
| GitBook win rate (weighted) | 48.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | GitBook | GitHub | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 5 | 34 | 26 | 90 | 13% |
| MiMo V2 Pro | Frontier | 13 | 0 | 4 | 115 | 100% |
| Gemini 2.5 Pro | Frontier | 0 | 13 | 2 | 152 | 0% |
| GLM 5 Turbo | Frontier | 7 | 0 | 43 | 81 | 100% |
| Claude Opus 4.6 | Frontier | 6 | 0 | 0 | 126 | 100% |
| GPT 5.4 | Frontier | 4 | 1 | 0 | 127 | 80% |
| GPT 5.5 | Frontier | 0 | 5 | 0 | 31 | 0% |
| MiniMax M2.7 | Frontier | 3 | 0 | 5 | 122 | 100% |
| DeepSeek R1 0528 | Frontier | 2 | 0 | 11 | 154 | 100% |
| DeepSeek V4 Flash | Mid | 2 | 0 | 1 | 32 | 100% |
| Gemini 2.5 Flash | Small | 2 | 0 | 0 | 130 | 100% |
| Kimi K2.7 Code | Frontier | 2 | 0 | 4 | 29 | 100% |
| MiMo V2.5 Pro | Frontier | 2 | 0 | 1 | 32 | 100% |
| DeepSeek V3.2 | Mid | 1 | 0 | 6 | 125 | 100% |
| DeepSeek V4 Pro | Frontier | 1 | 0 | 4 | 31 | 100% |
| Devstral 2 2512 | Mid | 1 | 0 | 0 | 161 | 100% |
| GPT 5.4 Mini | Mid | 1 | 0 | 7 | 153 | 100% |
| Claude Sonnet 4.6 | Frontier | 0 | 1 | 0 | 167 | 0% |
| Mistral Small 4 | Mid | 0 | 1 | 0 | 157 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 0 | 168 | n/a |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 36 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 5 | 31 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 0 | 36 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 6 | 158 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 9 | 121 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 5 | 158 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 0 | 36 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 58 | 110 | n/a |
| Prompt | Tier | GitBook | GitHub | None | Other | A rate |
|---|---|---|---|---|---|---|
| documentation-site | Intermediate | 41 | 30 | 30 | 422 | 58% |
| documentation-site | Advanced | 2 | 25 | 14 | 479 | 7% |
| documentation-site | Beginner | 9 | 0 | 123 | 397 | 100% |
| blog-platform-cms | Advanced | 0 | 0 | 30 | 498 | n/a |
| blog-platform-cms | Beginner | 0 | 0 | 0 | 537 | n/a |
| blog-platform-cms | Intermediate | 0 | 0 | 0 | 536 | n/a |
