| Metric | Value |
|---|---|
| Ghost wins | 441 |
| Contentful wins | 442 |
| Abstains (no tool) | 234 |
| Other tool chosen | 2033 |
| Decisive cases | 883 |
| Ghost win rate (unweighted) | 49.9% |
| 95% CI | 46.7% - 53.2% |
| Ghost win rate (weighted) | 49.9% |
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 | 40 | 62 | 0 | 59 | 39% |
| Llama 4 Scout | Small | 69 | 8 | 4 | 82 | 90% |
| Gemini 2.5 Pro | Frontier | 50 | 23 | 6 | 88 | 68% |
| Mistral Small 4 | Mid | 31 | 38 | 0 | 90 | 45% |
| MiniMax M2.7 | Frontier | 40 | 25 | 10 | 84 | 62% |
| Llama 4 Maverick | Frontier | 52 | 1 | 28 | 75 | 98% |
| Devstral 2 2512 | Mid | 25 | 23 | 5 | 115 | 52% |
| GLM 5 Turbo | Frontier | 31 | 13 | 51 | 65 | 70% |
| MiMo V2 Pro | Frontier | 17 | 27 | 10 | 108 | 39% |
| Claude Opus 4.6 | Frontier | 27 | 16 | 0 | 119 | 63% |
| GPT 5.3 Codex | Frontier | 2 | 37 | 12 | 114 | 5% |
| Qwen3 Coder Next | Mid | 4 | 32 | 53 | 79 | 11% |
| GPT 5.4 Mini | Mid | 0 | 35 | 8 | 119 | 0% |
| Claude Haiku 4.5 | Small | 0 | 34 | 8 | 126 | 0% |
| GPT 5.4 | Frontier | 14 | 18 | 0 | 130 | 44% |
| DeepSeek V3.2 | Mid | 5 | 24 | 7 | 125 | 17% |
| Claude Sonnet 4.6 | Frontier | 28 | 0 | 0 | 140 | 100% |
| DeepSeek R1 0528 | Frontier | 0 | 23 | 12 | 132 | 0% |
| DeepSeek V4 Flash | Mid | 1 | 1 | 0 | 4 | 50% |
| Claude Opus 4.8 | Frontier | 1 | 0 | 0 | 5 | 100% |
| DeepSeek V4 Pro | Frontier | 1 | 0 | 1 | 4 | 100% |
| Gemini 3.5 Flash | Small | 1 | 0 | 1 | 4 | 100% |
| GLM 5.2 | Frontier | 1 | 0 | 0 | 5 | 100% |
| GPT 5.5 | Frontier | 1 | 0 | 0 | 5 | 100% |
| Kimi K2.5 | Frontier | 0 | 1 | 17 | 142 | 0% |
| MiMo V2.5 Pro | Frontier | 0 | 1 | 0 | 4 | 0% |
| Kimi K2.7 Code | Frontier | 0 | 0 | 1 | 4 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 0 | 6 | n/a |
| Prompt | Tier | Ghost | Contentful | None | Other | A rate |
|---|---|---|---|---|---|---|
| blog-platform-cms | Beginner | 251 | 34 | 0 | 153 | 88% |
| documentation-site | Advanced | 0 | 185 | 14 | 224 | 0% |
| blog-platform-cms | Intermediate | 99 | 16 | 0 | 322 | 86% |
| documentation-site | Intermediate | 0 | 94 | 26 | 307 | 0% |
| blog-platform-cms | Advanced | 29 | 54 | 29 | 318 | 35% |
| blog-platform-cms | Beginner | 47 | 0 | 3 | 45 | 100% |
| documentation-site | Advanced | 0 | 33 | 2 | 60 | 0% |
| blog-platform-cms | Intermediate | 14 | 0 | 1 | 79 | 100% |
| documentation-site | Beginner | 0 | 13 | 96 | 322 | 0% |
| documentation-site | Intermediate | 0 | 12 | 11 | 68 | 0% |
| blog-platform-cms | Advanced | 1 | 1 | 28 | 65 | 50% |
| documentation-site | Beginner | 0 | 0 | 24 | 70 | n/a |
