| Metric | Value |
|---|---|
| Payload CMS wins | 75 |
| Strapi wins | 252 |
| Abstains (no tool) | 151 |
| Other tool chosen | 1878 |
| Decisive cases | 327 |
| Payload CMS win rate (unweighted) | 22.9% |
| 95% CI | 18.7% - 27.8% |
| Payload CMS win rate (weighted) | 22.9% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Payload CMS | Strapi | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek R1 0528 | Frontier | 0 | 53 | 9 | 63 | 0% |
| Claude Sonnet 4.6 | Frontier | 42 | 0 | 0 | 84 | 100% |
| Claude Haiku 4.5 | Small | 0 | 42 | 0 | 84 | 0% |
| MiMo V2 Pro | Frontier | 0 | 37 | 4 | 85 | 0% |
| DeepSeek V3.2 | Mid | 0 | 24 | 6 | 96 | 0% |
| GPT 5.4 | Frontier | 0 | 23 | 0 | 103 | 0% |
| Llama 4 Maverick | Frontier | 0 | 18 | 19 | 77 | 0% |
| MiniMax M2.7 | Frontier | 14 | 2 | 5 | 103 | 88% |
| Kimi K2.5 | Frontier | 14 | 0 | 9 | 101 | 100% |
| Gemini 2.5 Flash | Small | 0 | 14 | 0 | 112 | 0% |
| Gemini 2.5 Pro | Frontier | 0 | 12 | 2 | 112 | 0% |
| GPT 5.3 Codex | Frontier | 4 | 3 | 4 | 112 | 57% |
| GPT 5.4 Mini | Mid | 1 | 6 | 4 | 109 | 14% |
| Mistral Small 4 | Mid | 0 | 6 | 0 | 114 | 0% |
| Claude Opus 4.6 | Frontier | 0 | 5 | 0 | 121 | 0% |
| Devstral 2 2512 | Mid | 0 | 3 | 0 | 123 | 0% |
| GLM 5 Turbo | Frontier | 0 | 3 | 41 | 81 | 0% |
| Qwen3 Coder Next | Mid | 0 | 1 | 44 | 81 | 0% |
| Llama 4 Scout | Small | 0 | 0 | 4 | 117 | n/a |
| Prompt | Tier | Payload CMS | Strapi | None | Other | A rate |
|---|---|---|---|---|---|---|
| blog-platform-cms | Advanced | 53 | 130 | 28 | 182 | 29% |
| blog-platform-cms | Intermediate | 22 | 79 | 0 | 298 | 22% |
| blog-platform-cms | Beginner | 0 | 18 | 0 | 381 | 0% |
| documentation-site | Advanced | 0 | 16 | 13 | 355 | 0% |
| documentation-site | Intermediate | 0 | 9 | 23 | 357 | 0% |
| documentation-site | Beginner | 0 | 0 | 87 | 305 | n/a |