| Metric | Value |
|---|---|
| GitHub wins | 37 |
| WordPress wins | 38 |
| Abstains (no tool) | 151 |
| Other tool chosen | 2130 |
| Decisive cases | 75 |
| GitHub win rate (unweighted) | 49.3% |
| 95% CI | 38.3% - 60.4% |
| GitHub win rate (weighted) | 49.3% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | GitHub | WordPress | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 24 | 0 | 19 | 71 | 100% |
| Devstral 2 2512 | Mid | 0 | 16 | 0 | 110 | 0% |
| Gemini 2.5 Pro | Frontier | 10 | 0 | 2 | 114 | 100% |
| DeepSeek V3.2 | Mid | 0 | 9 | 6 | 111 | 0% |
| Llama 4 Scout | Small | 0 | 6 | 4 | 111 | 0% |
| MiniMax M2.7 | Frontier | 0 | 3 | 5 | 116 | 0% |
| DeepSeek R1 0528 | Frontier | 0 | 2 | 9 | 114 | 0% |
| Claude Sonnet 4.6 | Frontier | 1 | 0 | 0 | 125 | 100% |
| GPT 5.4 | Frontier | 1 | 0 | 0 | 125 | 100% |
| Mistral Small 4 | Mid | 1 | 0 | 0 | 119 | 100% |
| GPT 5.4 Mini | Mid | 0 | 1 | 4 | 115 | 0% |
| MiMo V2 Pro | Frontier | 0 | 1 | 4 | 121 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 0 | 126 | n/a |
| Claude Opus 4.6 | Frontier | 0 | 0 | 0 | 126 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 0 | 126 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 41 | 84 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 4 | 119 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 9 | 115 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 44 | 82 | n/a |
| Prompt | Tier | GitHub | WordPress | None | Other | A rate |
|---|---|---|---|---|---|---|
| blog-platform-cms | Intermediate | 0 | 29 | 0 | 370 | 0% |
| documentation-site | Intermediate | 20 | 0 | 23 | 346 | 100% |
| documentation-site | Advanced | 17 | 0 | 13 | 354 | 100% |
| blog-platform-cms | Beginner | 0 | 9 | 0 | 390 | 0% |
| blog-platform-cms | Advanced | 0 | 0 | 28 | 365 | n/a |
| documentation-site | Beginner | 0 | 0 | 87 | 305 | n/a |