| Metric | Value |
|---|---|
| Contentful wins | 559 |
| Ghost wins | 590 |
| Abstains (no tool) | 350 |
| Other tool chosen | 2996 |
| Decisive cases | 1149 |
| Contentful win rate (unweighted) | 48.7% |
| 95% CI | 45.8% - 51.5% |
| Contentful win rate (weighted) | 48.7% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Contentful | Ghost | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 32 | 12 | 9 | 183 | 73% |
| DeepSeek Pro 4–4 0813 | Frontier | 1 | 8 | 6 | 39 | 11% |
| DeepSeek R1 | Frontier | 35 | 0 | 16 | 186 | 100% |
| Devstral | Mid | 29 | 36 | 8 | 153 | 45% |
| Gemini Flash 2.5–3.8 | Small | 64 | 48 | 8 | 117 | 57% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 29 | 64 | 7 | 136 | 31% |
| GLM 5 Turbo–5.3 | Frontier | 15 | 41 | 59 | 121 | 27% |
| GPT 5.4–6 Astra | Frontier | 21 | 20 | 3 | 194 | 51% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 45 | 5 | 22 | 162 | 90% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 46 | 1 | 14 | 168 | 98% |
| Haiku | Small | 48 | 0 | 19 | 171 | 100% |
| Kimi 2.5–3 | Frontier | 1 | 1 | 29 | 203 | 50% |
| Llama Maverick | Frontier | 5 | 69 | 38 | 113 | 7% |
| Llama Scout | Small | 12 | 98 | 6 | 115 | 11% |
| MiMo Pro 2–2.6 | Frontier | 35 | 22 | 15 | 163 | 61% |
| MiniMax M 2.7–3 | Frontier | 28 | 43 | 14 | 149 | 39% |
| Mistral Small | Mid | 47 | 45 | 0 | 133 | 51% |
| Opus 4.6–5.5 | Frontier | 16 | 33 | 2 | 186 | 33% |
| Qwen Coder | Mid | 50 | 4 | 71 | 110 | 93% |
| Sonnet 4.6–5.5 | Frontier | 0 | 40 | 4 | 194 | 0% |
| Prompt | Tier | Contentful | Ghost | None | Other | A rate |
|---|---|---|---|---|---|---|
| blog-platform-cms | Beginner | 47 | 324 | 0 | 225 | 13% |
| documentation-site | Advanced | 228 | 0 | 15 | 335 | 100% |
| blog-platform-cms | Intermediate | 25 | 127 | 0 | 443 | 16% |
| documentation-site | Intermediate | 105 | 0 | 39 | 438 | 100% |
| blog-platform-cms | Advanced | 61 | 39 | 32 | 455 | 61% |
| blog-platform-cms | Beginner | 3 | 77 | 5 | 84 | 4% |
| documentation-site | Advanced | 52 | 0 | 5 | 111 | 100% |
| documentation-site | Intermediate | 20 | 0 | 23 | 119 | 100% |
| blog-platform-cms | Intermediate | 0 | 20 | 2 | 129 | 0% |
| documentation-site | Beginner | 17 | 0 | 143 | 428 | 100% |
| blog-platform-cms | Advanced | 1 | 3 | 47 | 117 | 25% |
| documentation-site | Beginner | 0 | 0 | 39 | 112 | n/a |
