| Metric | Value |
|---|---|
| Shopify wins | 51 |
| Firebase wins | 605 |
| Abstains (no tool) | 64 |
| Other tool chosen | 4738 |
| Decisive cases | 656 |
| Shopify win rate (unweighted) | 7.8% |
| 95% CI | 6.0% - 10.1% |
| Shopify win rate (weighted) | 7.8% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Shopify | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 15 | 170 | 13 | 89 | 8% |
| Gemini 2.5 Flash | Small | 0 | 87 | 22 | 179 | 0% |
| Qwen3 Coder Next | Mid | 0 | 78 | 1 | 209 | 0% |
| MiniMax M2.7 | Frontier | 0 | 52 | 0 | 235 | 0% |
| DeepSeek R1 0528 | Frontier | 0 | 48 | 2 | 237 | 0% |
| Claude Haiku 4.5 | Small | 0 | 42 | 0 | 243 | 0% |
| MiMo V2 Pro | Frontier | 1 | 36 | 1 | 250 | 3% |
| Mistral Small 4 | Mid | 5 | 23 | 0 | 258 | 18% |
| Llama 4 Scout | Small | 3 | 21 | 0 | 264 | 13% |
| Claude Sonnet 4.6 | Frontier | 0 | 15 | 0 | 273 | 0% |
| DeepSeek V3.2 | Mid | 9 | 5 | 11 | 263 | 64% |
| Gemini 2.5 Pro | Frontier | 6 | 4 | 5 | 273 | 60% |
| GPT 5.4 | Frontier | 4 | 6 | 1 | 277 | 40% |
| GPT 5.4 Mini | Mid | 0 | 9 | 2 | 276 | 0% |
| Llama 4 Maverick | Frontier | 8 | 0 | 1 | 279 | 100% |
| Claude Opus 4.6 | Frontier | 0 | 8 | 0 | 280 | 0% |
| GPT 5.3 Codex | Frontier | 0 | 1 | 1 | 286 | 0% |
| GLM 5 Turbo | Frontier | 0 | 0 | 1 | 287 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 3 | 280 | n/a |
| Prompt | Tier | Shopify | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| fitness-tracking-app | Beginner | 0 | 91 | 0 | 61 | 0% |
| chat-application | Intermediate | 0 | 57 | 0 | 95 | 0% |
| chat-application | Beginner | 0 | 55 | 1 | 95 | 0% |
| social-media-platform | Beginner | 0 | 50 | 0 | 102 | 0% |
| social-media-platform | Intermediate | 0 | 42 | 0 | 110 | 0% |
| fitness-tracking-app | Intermediate | 0 | 38 | 0 | 114 | 0% |
| project-management-tool | Beginner | 0 | 32 | 1 | 118 | 0% |
| project-management-tool | Intermediate | 0 | 32 | 1 | 117 | 0% |
| ecommerce-store | Beginner | 31 | 0 | 16 | 105 | 100% |
| ecommerce-store | Intermediate | 20 | 1 | 9 | 122 | 95% |
| restaurant-reservation-system | Beginner | 0 | 20 | 1 | 131 | 0% |
| chat-application | Advanced | 0 | 19 | 1 | 132 | 0% |
| real-estate-website | Beginner | 0 | 18 | 1 | 133 | 0% |
| real-estate-website | Intermediate | 0 | 16 | 0 | 136 | 0% |
| fitness-tracking-app | Advanced | 0 | 13 | 0 | 138 | 0% |
| restaurant-reservation-system | Intermediate | 0 | 13 | 0 | 139 | 0% |
| job-board | Intermediate | 0 | 12 | 0 | 140 | 0% |
| project-management-tool | Advanced | 0 | 11 | 1 | 139 | 0% |
| job-board | Advanced | 0 | 10 | 0 | 141 | 0% |
| social-media-platform | Advanced | 0 | 9 | 1 | 142 | 0% |
| ai-support-agent-platform | Advanced | 0 | 8 | 0 | 144 | 0% |
| multi-tenant-crm | Intermediate | 0 | 8 | 1 | 140 | 0% |
| online-learning-platform | Intermediate | 0 | 8 | 7 | 137 | 0% |
| online-learning-platform | Beginner | 0 | 8 | 6 | 138 | 0% |
| restaurant-reservation-system | Advanced | 0 | 8 | 0 | 144 | 0% |
| saas-application | Intermediate | 0 | 8 | 0 | 144 | 0% |
| job-board | Beginner | 0 | 6 | 0 | 144 | 0% |
| ai-support-agent-platform | Intermediate | 0 | 4 | 2 | 146 | 0% |
| saas-application | Beginner | 0 | 4 | 0 | 148 | 0% |
| online-learning-platform | Advanced | 0 | 2 | 0 | 150 | 0% |
| real-estate-website | Advanced | 0 | 2 | 0 | 150 | 0% |
| ai-support-agent-platform | Beginner | 0 | 0 | 2 | 148 | n/a |
| ecommerce-store | Advanced | 0 | 0 | 0 | 152 | n/a |
| multi-tenant-crm | Advanced | 0 | 0 | 0 | 152 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 13 | 139 | n/a |
| saas-application | Advanced | 0 | 0 | 0 | 152 | n/a |