| Metric | Value |
|---|---|
| Sanity wins | 780 |
| Contentful wins | 450 |
| Abstains (no tool) | 197 |
| Other tool chosen | 1747 |
| Decisive cases | 1230 |
| Sanity win rate (unweighted) | 63.4% |
| 95% CI | 60.7% - 66.1% |
| Sanity win rate (weighted) | 63.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Sanity | Contentful | None | Other | A rate |
|---|---|---|---|---|---|---|
| GPT 5.4 Mini | Mid | 91 | 33 | 7 | 30 | 73% |
| GPT 5.3 Codex | Frontier | 78 | 36 | 7 | 43 | 68% |
| Qwen3 Coder Next | Mid | 60 | 38 | 56 | 14 | 61% |
| Kimi K2.5 | Frontier | 87 | 1 | 8 | 28 | 99% |
| Mistral Small 4 | Mid | 45 | 42 | 0 | 72 | 52% |
| DeepSeek V3.2 | Mid | 41 | 19 | 6 | 60 | 68% |
| Claude Opus 4.6 | Frontier | 42 | 15 | 0 | 69 | 74% |
| GPT 5.4 | Frontier | 39 | 17 | 0 | 70 | 70% |
| Gemini 2.5 Flash | Small | 0 | 56 | 0 | 70 | 0% |
| DeepSeek R1 0528 | Frontier | 19 | 30 | 11 | 107 | 39% |
| Gemini 2.5 Pro | Frontier | 19 | 27 | 2 | 119 | 41% |
| GLM 5 Turbo | Frontier | 33 | 9 | 41 | 42 | 79% |
| MiniMax M2.7 | Frontier | 15 | 22 | 4 | 83 | 41% |
| Claude Haiku 4.5 | Small | 0 | 34 | 0 | 134 | 0% |
| MiMo V2 Pro | Frontier | 8 | 23 | 4 | 91 | 26% |
| Kimi K2.7 Code | Frontier | 29 | 0 | 5 | 7 | 100% |
| MiniMax M3 | Frontier | 27 | 1 | 0 | 14 | 96% |
| Claude Sonnet 4.6 | Frontier | 27 | 0 | 0 | 141 | 100% |
| Gemini 3.5 Flash | Small | 26 | 0 | 6 | 10 | 100% |
| GLM 5.2 | Frontier | 26 | 0 | 0 | 16 | 100% |
| Devstral 2 2512 | Mid | 0 | 26 | 0 | 130 | 0% |
| Claude Opus 4.8 | Frontier | 21 | 0 | 0 | 21 | 100% |
| DeepSeek V4 Pro | Frontier | 18 | 1 | 6 | 17 | 95% |
| GPT 5.5 | Frontier | 14 | 2 | 0 | 26 | 88% |
| MiMo V2.5 Pro | Frontier | 10 | 6 | 1 | 24 | 63% |
| DeepSeek V4 Flash | Mid | 5 | 5 | 1 | 30 | 50% |
| Llama 4 Scout | Small | 0 | 5 | 6 | 152 | 0% |
| Llama 4 Maverick | Frontier | 0 | 2 | 26 | 127 | 0% |
| Prompt | Tier | Sanity | Contentful | None | Other | A rate |
|---|---|---|---|---|---|---|
| documentation-site | Advanced | 177 | 215 | 13 | 115 | 45% |
| blog-platform-cms | Intermediate | 234 | 23 | 0 | 279 | 91% |
| documentation-site | Intermediate | 113 | 96 | 30 | 284 | 54% |
| blog-platform-cms | Beginner | 131 | 44 | 0 | 362 | 75% |
| blog-platform-cms | Advanced | 115 | 55 | 30 | 328 | 68% |
| documentation-site | Beginner | 10 | 17 | 124 | 379 | 37% |
