| Metric | Value |
|---|---|
| Ghost wins | 446 |
| Contentful wins | 450 |
| Abstains (no tool) | 197 |
| Other tool chosen | 2081 |
| Decisive cases | 896 |
| Ghost win rate (unweighted) | 49.8% |
| 95% CI | 46.5% - 53.0% |
| Ghost win rate (weighted) | 49.8% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Ghost | Contentful | None | Other | A rate |
|---|---|---|---|---|---|---|
| Gemini 2.5 Flash | Small | 33 | 56 | 0 | 37 | 37% |
| Llama 4 Scout | Small | 74 | 5 | 6 | 78 | 94% |
| Gemini 2.5 Pro | Frontier | 52 | 27 | 2 | 86 | 66% |
| Mistral Small 4 | Mid | 29 | 42 | 0 | 88 | 41% |
| Llama 4 Maverick | Frontier | 58 | 2 | 26 | 69 | 97% |
| MiniMax M2.7 | Frontier | 33 | 22 | 4 | 65 | 60% |
| Devstral 2 2512 | Mid | 22 | 26 | 0 | 108 | 46% |
| Qwen3 Coder Next | Mid | 2 | 38 | 56 | 72 | 5% |
| MiMo V2 Pro | Frontier | 15 | 23 | 4 | 84 | 39% |
| GPT 5.3 Codex | Frontier | 2 | 36 | 7 | 119 | 5% |
| Claude Opus 4.6 | Frontier | 21 | 15 | 0 | 90 | 58% |
| GLM 5 Turbo | Frontier | 25 | 9 | 41 | 50 | 74% |
| Claude Haiku 4.5 | Small | 0 | 34 | 0 | 134 | 0% |
| GPT 5.4 Mini | Mid | 0 | 33 | 7 | 121 | 0% |
| GPT 5.4 | Frontier | 14 | 17 | 0 | 95 | 45% |
| Claude Sonnet 4.6 | Frontier | 30 | 0 | 0 | 138 | 100% |
| DeepSeek R1 0528 | Frontier | 0 | 30 | 11 | 126 | 0% |
| DeepSeek V3.2 | Mid | 4 | 19 | 6 | 97 | 17% |
| DeepSeek V4 Flash | Mid | 7 | 5 | 1 | 28 | 58% |
| MiMo V2.5 Pro | Frontier | 4 | 6 | 1 | 30 | 40% |
| DeepSeek V4 Pro | Frontier | 7 | 1 | 6 | 28 | 88% |
| GPT 5.5 | Frontier | 4 | 2 | 0 | 36 | 67% |
| Gemini 3.5 Flash | Small | 5 | 0 | 6 | 31 | 100% |
| GLM 5.2 | Frontier | 2 | 0 | 0 | 40 | 100% |
| MiniMax M3 | Frontier | 1 | 1 | 0 | 40 | 50% |
| Claude Opus 4.8 | Frontier | 1 | 0 | 0 | 41 | 100% |
| Kimi K2.7 Code | Frontier | 1 | 0 | 5 | 35 | 100% |
| Kimi K2.5 | Frontier | 0 | 1 | 8 | 115 | 0% |
| Prompt | Tier | Ghost | Contentful | None | Other | A rate |
|---|---|---|---|---|---|---|
| blog-platform-cms | Beginner | 296 | 44 | 0 | 197 | 87% |
| documentation-site | Advanced | 0 | 215 | 13 | 292 | 0% |
| blog-platform-cms | Intermediate | 114 | 23 | 0 | 399 | 83% |
| documentation-site | Intermediate | 0 | 96 | 30 | 397 | 0% |
| blog-platform-cms | Advanced | 36 | 55 | 30 | 407 | 40% |
| documentation-site | Beginner | 0 | 17 | 124 | 389 | 0% |
