| Metric | Value |
|---|---|
| Strapi wins | 334 |
| Ghost wins | 450 |
| Abstains (no tool) | 197 |
| Other tool chosen | 2192 |
| Decisive cases | 784 |
| Strapi win rate (unweighted) | 42.6% |
| 95% CI | 39.2% - 46.1% |
| Strapi win rate (weighted) | 42.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Strapi | Ghost | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 25 | 58 | 26 | 46 | 30% |
| Llama 4 Scout | Small | 0 | 75 | 5 | 83 | 0% |
| DeepSeek R1 0528 | Frontier | 71 | 0 | 11 | 85 | 100% |
| Gemini 2.5 Pro | Frontier | 15 | 52 | 2 | 98 | 22% |
| Claude Haiku 4.5 | Small | 56 | 0 | 0 | 112 | 100% |
| MiMo V2 Pro | Frontier | 39 | 16 | 4 | 73 | 71% |
| Gemini 2.5 Flash | Small | 14 | 35 | 0 | 83 | 29% |
| Mistral Small 4 | Mid | 10 | 29 | 0 | 119 | 26% |
| GPT 5.4 | Frontier | 24 | 14 | 0 | 94 | 63% |
| MiniMax M2.7 | Frontier | 2 | 34 | 5 | 89 | 6% |
| GLM 5 Turbo | Frontier | 4 | 26 | 43 | 58 | 13% |
| Claude Sonnet 4.6 | Frontier | 0 | 30 | 0 | 138 | 0% |
| DeepSeek V3.2 | Mid | 24 | 4 | 6 | 98 | 86% |
| Claude Opus 4.6 | Frontier | 5 | 22 | 0 | 105 | 19% |
| Devstral 2 2512 | Mid | 3 | 23 | 0 | 136 | 12% |
| DeepSeek V4 Flash | Mid | 11 | 6 | 1 | 17 | 65% |
| DeepSeek V4 Pro | Frontier | 2 | 7 | 4 | 23 | 22% |
| GPT 5.4 Mini | Mid | 8 | 0 | 7 | 146 | 100% |
| MiMo V2.5 Pro | Frontier | 5 | 3 | 1 | 26 | 63% |
| GLM 5.2 | Frontier | 5 | 2 | 0 | 29 | 71% |
| GPT 5.3 Codex | Frontier | 5 | 2 | 6 | 151 | 71% |
| MiniMax M3 | Frontier | 4 | 1 | 0 | 31 | 80% |
| Gemini 3.5 Flash | Small | 1 | 4 | 5 | 26 | 20% |
| Qwen3 Coder Next | Mid | 1 | 2 | 58 | 107 | 33% |
| GPT 5.5 | Frontier | 0 | 3 | 0 | 33 | 0% |
| Claude Opus 4.8 | Frontier | 0 | 1 | 0 | 35 | 0% |
| Kimi K2.7 Code | Frontier | 0 | 1 | 4 | 30 | 0% |
| Kimi K2.5 | Frontier | 0 | 0 | 9 | 121 | n/a |
| Prompt | Tier | Strapi | Ghost | None | Other | A rate |
|---|---|---|---|---|---|---|
| blog-platform-cms | Beginner | 23 | 298 | 0 | 216 | 7% |
| blog-platform-cms | Advanced | 180 | 36 | 30 | 282 | 83% |
| blog-platform-cms | Intermediate | 100 | 116 | 0 | 320 | 46% |
| documentation-site | Advanced | 20 | 0 | 14 | 486 | 100% |
| documentation-site | Intermediate | 11 | 0 | 30 | 482 | 100% |
| documentation-site | Beginner | 0 | 0 | 123 | 406 | n/a |
