| Metric | Value |
|---|---|
| Customer.io wins | 19 |
| Ghost wins | 23 |
| Abstains (no tool) | 192 |
| Other tool chosen | 15634 |
| Decisive cases | 42 |
| Customer.io win rate (unweighted) | 45.2% |
| 95% CI | 31.2% - 60.1% |
| Customer.io win rate (weighted) | 45.2% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Customer.io | Ghost | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 0 | 2 | 9 | 810 | 0% |
| DeepSeek Pro 4–4 0813 | Frontier | 0 | 0 | 2 | 187 | n/a |
| DeepSeek R1 | Frontier | 0 | 0 | 10 | 821 | n/a |
| Devstral | Mid | 0 | 0 | 0 | 787 | n/a |
| Gemini Flash 2.5–3.8 | Small | 1 | 0 | 13 | 816 | 100% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 1 | 0 | 15 | 814 | 100% |
| GLM 5 Turbo–5.3 | Frontier | 1 | 0 | 24 | 805 | 100% |
| GPT 5.4–6 Astra | Frontier | 4 | 7 | 3 | 815 | 36% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 10 | 1 | 6 | 814 | 91% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 2 | 0 | 12 | 814 | 100% |
| Haiku | Small | 0 | 0 | 18 | 808 | n/a |
| Kimi 2.5–3 | Frontier | 0 | 0 | 14 | 810 | n/a |
| Llama Maverick | Frontier | 0 | 0 | 0 | 831 | n/a |
| Llama Scout | Small | 0 | 0 | 32 | 797 | n/a |
| MiMo Pro 2–2.6 | Frontier | 0 | 0 | 4 | 819 | n/a |
| MiniMax M 2.7–3 | Frontier | 0 | 10 | 8 | 809 | 0% |
| Mistral Small | Mid | 0 | 3 | 0 | 817 | 0% |
| Opus 4.6–5.5 | Frontier | 0 | 0 | 9 | 822 | n/a |
| Qwen Coder | Mid | 0 | 0 | 13 | 807 | n/a |
| Sonnet 4.6–5.5 | Frontier | 0 | 0 | 0 | 831 | n/a |
| Prompt | Tier | Customer.io | Ghost | None | Other | A rate |
|---|---|---|---|---|---|---|
| blog-platform-cms | Beginner | 0 | 22 | 37 | 525 | 0% |
| blog-platform-cms | Advanced | 14 | 0 | 3 | 576 | 100% |
| multi-tenant-crm | Advanced | 5 | 0 | 4 | 586 | 100% |
| blog-platform-cms | Intermediate | 0 | 1 | 2 | 591 | 0% |
| blog-platform-cms | Intermediate | 0 | 0 | 0 | 152 | n/a |
| blog-platform-cms | Beginner | 0 | 0 | 6 | 163 | n/a |
| blog-platform-cms | Advanced | 0 | 0 | 0 | 168 | n/a |
| ecommerce-store | Beginner | 0 | 0 | 8 | 143 | n/a |
| ecommerce-store | Beginner | 0 | 0 | 16 | 577 | n/a |
| ecommerce-store | Advanced | 0 | 0 | 3 | 149 | n/a |
| ecommerce-store | Advanced | 0 | 0 | 2 | 594 | n/a |
| ecommerce-store | Intermediate | 0 | 0 | 2 | 594 | n/a |
| ecommerce-store | Intermediate | 0 | 0 | 0 | 168 | n/a |
| job-board | Beginner | 0 | 0 | 0 | 169 | n/a |
| job-board | Advanced | 0 | 0 | 1 | 595 | n/a |
| job-board | Intermediate | 0 | 0 | 0 | 152 | n/a |
| job-board | Beginner | 0 | 0 | 0 | 595 | n/a |
| job-board | Advanced | 0 | 0 | 1 | 170 | n/a |
| job-board | Intermediate | 0 | 0 | 0 | 596 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 1 | 163 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 3 | 581 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 0 | 152 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 1 | 589 | n/a |
| multi-tenant-crm | Advanced | 0 | 0 | 2 | 168 | n/a |
| online-learning-platform | Advanced | 0 | 0 | 4 | 148 | n/a |
| online-learning-platform | Beginner | 0 | 0 | 6 | 164 | n/a |
| online-learning-platform | Advanced | 0 | 0 | 7 | 589 | n/a |
| online-learning-platform | Intermediate | 0 | 0 | 0 | 151 | n/a |
| online-learning-platform | Intermediate | 0 | 0 | 1 | 593 | n/a |
| online-learning-platform | Beginner | 0 | 0 | 2 | 593 | n/a |
| restaurant-reservation-system | Advanced | 0 | 0 | 3 | 149 | n/a |
| restaurant-reservation-system | Intermediate | 0 | 0 | 10 | 586 | n/a |
| restaurant-reservation-system | Intermediate | 0 | 0 | 1 | 170 | n/a |
| restaurant-reservation-system | Beginner | 0 | 0 | 9 | 587 | n/a |
| restaurant-reservation-system | Beginner | 0 | 0 | 0 | 152 | n/a |
| restaurant-reservation-system | Advanced | 0 | 0 | 5 | 591 | n/a |
| saas-application | Advanced | 0 | 0 | 32 | 563 | n/a |
| saas-application | Advanced | 0 | 0 | 9 | 161 | n/a |
| saas-application | Intermediate | 0 | 0 | 0 | 171 | n/a |
| saas-application | Beginner | 0 | 0 | 3 | 593 | n/a |
| saas-application | Intermediate | 0 | 0 | 5 | 591 | n/a |
| saas-application | Beginner | 0 | 0 | 3 | 166 | n/a |
