| Metric | Value |
|---|---|
| Railway wins | 987 |
| Firebase wins | 1168 |
| Abstains (no tool) | 643 |
| Other tool chosen | 35742 |
| Decisive cases | 2155 |
| Railway win rate (unweighted) | 45.8% |
| 95% CI | 43.7% - 47.9% |
| Railway win rate (weighted) | 45.8% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Railway | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 37 | 12 | 32 | 1924 | 76% |
| DeepSeek Pro 4–4 0813 | Frontier | 37 | 13 | 2 | 460 | 74% |
| DeepSeek R1 | Frontier | 0 | 199 | 15 | 1800 | 0% |
| Devstral | Mid | 6 | 253 | 79 | 1559 | 2% |
| Gemini Flash 2.5–3.8 | Small | 0 | 43 | 62 | 1908 | 0% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 3 | 5 | 19 | 1987 | 38% |
| GLM 5 Turbo–5.3 | Frontier | 71 | 0 | 71 | 1875 | 100% |
| GPT 5.4–6 Astra | Frontier | 9 | 13 | 1 | 1993 | 41% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 19 | 11 | 1 | 1983 | 63% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 1 | 10 | 41 | 1952 | 9% |
| Haiku | Small | 57 | 39 | 30 | 1844 | 59% |
| Kimi 2.5–3 | Frontier | 153 | 0 | 29 | 1805 | 100% |
| Llama Maverick | Frontier | 0 | 17 | 16 | 1985 | 0% |
| Llama Scout | Small | 0 | 99 | 115 | 1795 | 0% |
| MiMo Pro 2–2.6 | Frontier | 24 | 106 | 26 | 1849 | 18% |
| MiniMax M 2.7–3 | Frontier | 121 | 41 | 30 | 1814 | 75% |
| Mistral Small | Mid | 20 | 97 | 15 | 1862 | 17% |
| Opus 4.6–5.5 | Frontier | 93 | 5 | 12 | 1908 | 95% |
| Qwen Coder | Mid | 0 | 205 | 45 | 1759 | 0% |
| Sonnet 4.6–5.5 | Frontier | 336 | 0 | 2 | 1680 | 100% |
| Prompt | Tier | Railway | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| fitness-tracking-app | Beginner | 0 | 214 | 4 | 372 | 0% |
| chat-application | Beginner | 3 | 138 | 0 | 450 | 2% |
| chat-application | Intermediate | 20 | 101 | 4 | 471 | 17% |
| social-media-platform | Beginner | 5 | 71 | 9 | 510 | 7% |
| project-management-tool | Advanced | 50 | 25 | 23 | 496 | 67% |
| ai-revenue-ops-copilot | Intermediate | 73 | 0 | 2 | 510 | 100% |
| project-management-tool | Beginner | 4 | 65 | 0 | 525 | 6% |
| chat-application | Intermediate | 34 | 30 | 11 | 95 | 53% |
| project-management-tool | Intermediate | 1 | 63 | 4 | 525 | 2% |
| chat-application | Beginner | 8 | 52 | 9 | 98 | 13% |
| url-shortener | Intermediate | 30 | 24 | 2 | 538 | 56% |
| fitness-tracking-app | Beginner | 0 | 54 | 5 | 111 | 0% |
| blog-platform-cms | Advanced | 53 | 0 | 6 | 532 | 100% |
| social-media-platform | Intermediate | 8 | 44 | 2 | 540 | 15% |
| url-shortener | Beginner | 6 | 43 | 6 | 541 | 12% |
| ai-agent-application | Beginner | 48 | 0 | 0 | 130 | 100% |
| chat-application | Advanced | 27 | 17 | 16 | 535 | 61% |
| ai-revenue-ops-copilot | Advanced | 40 | 0 | 16 | 511 | 100% |
| restaurant-reservation-system | Advanced | 37 | 3 | 3 | 553 | 93% |
| url-shortener | Intermediate | 34 | 1 | 0 | 117 | 97% |
| ai-revenue-ops-copilot | Beginner | 34 | 0 | 2 | 552 | 100% |
| multi-tenant-crm | Intermediate | 34 | 0 | 2 | 552 | 100% |
| full-stack-web-app | Intermediate | 33 | 0 | 0 | 145 | 100% |
| social-media-platform | Beginner | 2 | 30 | 4 | 135 | 6% |
| ai-support-agent-platform | Intermediate | 28 | 3 | 2 | 562 | 90% |
| ai-agent-application | Intermediate | 29 | 0 | 1 | 148 | 100% |
| ecommerce-store | Advanced | 28 | 0 | 5 | 562 | 100% |
| full-stack-web-app | Beginner | 26 | 0 | 0 | 152 | 100% |
| online-learning-platform | Advanced | 23 | 0 | 4 | 564 | 100% |
| blog-platform-cms | Advanced | 21 | 0 | 2 | 144 | 100% |
| restaurant-reservation-system | Intermediate | 13 | 7 | 0 | 576 | 65% |
| fitness-tracking-app | Intermediate | 0 | 20 | 1 | 575 | 0% |
| url-shortener | Beginner | 10 | 9 | 2 | 130 | 53% |
| job-board | Advanced | 18 | 0 | 4 | 573 | 100% |
| real-estate-website | Advanced | 17 | 0 | 2 | 574 | 100% |
| saas-application | Advanced | 17 | 0 | 28 | 550 | 100% |
| social-media-platform | Intermediate | 7 | 10 | 2 | 130 | 41% |
| restaurant-reservation-system | Advanced | 15 | 0 | 3 | 134 | 100% |
| project-management-tool | Intermediate | 2 | 13 | 2 | 134 | 13% |
| multi-tenant-crm | Advanced | 14 | 0 | 16 | 566 | 100% |
| job-board | Intermediate | 4 | 10 | 1 | 581 | 29% |
| real-estate-website | Beginner | 0 | 13 | 2 | 581 | 0% |
| weather-dashboard | Intermediate | 0 | 13 | 3 | 577 | 0% |
| saas-application | Beginner | 1 | 11 | 1 | 583 | 8% |
| multi-tenant-crm | Intermediate | 11 | 0 | 11 | 130 | 100% |
| restaurant-reservation-system | Intermediate | 11 | 0 | 4 | 156 | 100% |
| ai-support-agent-platform | Advanced | 10 | 0 | 3 | 568 | 100% |
| online-learning-platform | Beginner | 3 | 7 | 5 | 579 | 30% |
| job-board | Beginner | 1 | 9 | 1 | 585 | 10% |
| online-learning-platform | Intermediate | 8 | 1 | 9 | 134 | 89% |
| fitness-tracking-app | Advanced | 4 | 5 | 5 | 578 | 44% |
| project-management-tool | Beginner | 0 | 9 | 2 | 140 | 0% |
| restaurant-reservation-system | Beginner | 0 | 9 | 2 | 585 | 0% |
| blog-platform-cms | Intermediate | 8 | 0 | 1 | 585 | 100% |
| real-estate-website | Beginner | 0 | 8 | 2 | 142 | 0% |
| blog-platform-cms | Intermediate | 7 | 0 | 7 | 138 | 100% |
| multi-tenant-crm | Beginner | 7 | 0 | 42 | 544 | 100% |
| real-estate-website | Advanced | 7 | 0 | 1 | 162 | 100% |
| ai-support-agent-platform | Beginner | 6 | 1 | 7 | 577 | 86% |
| online-learning-platform | Intermediate | 4 | 3 | 15 | 574 | 57% |
| real-estate-website | Intermediate | 0 | 7 | 0 | 589 | 0% |
| ecommerce-store | Intermediate | 5 | 0 | 3 | 161 | 100% |
| job-board | Intermediate | 5 | 0 | 6 | 140 | 100% |
| restaurant-reservation-system | Beginner | 2 | 3 | 4 | 143 | 40% |
| blog-platform-cms | Beginner | 4 | 0 | 1 | 588 | 100% |
| online-learning-platform | Beginner | 2 | 2 | 3 | 162 | 50% |
| weather-dashboard | Advanced | 2 | 2 | 0 | 588 | 50% |
| job-board | Beginner | 0 | 4 | 4 | 163 | 0% |
| blog-platform-cms | Beginner | 3 | 0 | 6 | 160 | 100% |
| multi-tenant-crm | Advanced | 3 | 0 | 7 | 160 | 100% |
| saas-application | Intermediate | 3 | 0 | 4 | 589 | 100% |
| multi-tenant-crm | Beginner | 2 | 1 | 7 | 154 | 67% |
| social-media-platform | Advanced | 2 | 1 | 10 | 580 | 67% |
| url-shortener | Advanced | 0 | 3 | 2 | 589 | 0% |
| weather-dashboard | Beginner | 0 | 3 | 14 | 151 | 0% |
| ecommerce-store | Intermediate | 2 | 0 | 3 | 591 | 100% |
| saas-application | Intermediate | 2 | 0 | 0 | 169 | 100% |
| project-management-tool | Advanced | 1 | 1 | 12 | 137 | 50% |
| fitness-tracking-app | Intermediate | 0 | 2 | 0 | 150 | 0% |
| weather-dashboard | Beginner | 0 | 2 | 3 | 591 | 0% |
| fitness-tracking-app | Advanced | 1 | 0 | 1 | 169 | 100% |
| job-board | Advanced | 1 | 0 | 7 | 163 | 100% |
| online-learning-platform | Advanced | 1 | 0 | 8 | 143 | 100% |
| saas-application | Advanced | 1 | 0 | 17 | 152 | 100% |
| url-shortener | Advanced | 1 | 0 | 6 | 144 | 100% |
| saas-application | Beginner | 0 | 1 | 0 | 168 | 0% |
| ai-agent-application | Advanced | 0 | 0 | 2 | 176 | n/a |
| chat-application | Advanced | 0 | 0 | 14 | 138 | n/a |
| documentation-site | Beginner | 0 | 0 | 17 | 135 | n/a |
| documentation-site | Beginner | 0 | 0 | 13 | 583 | n/a |
| documentation-site | Intermediate | 0 | 0 | 9 | 158 | n/a |
| documentation-site | Advanced | 0 | 0 | 3 | 166 | n/a |
| documentation-site | Intermediate | 0 | 0 | 17 | 577 | n/a |
| documentation-site | Advanced | 0 | 0 | 0 | 594 | n/a |
| ecommerce-store | Beginner | 0 | 0 | 21 | 130 | n/a |
| ecommerce-store | Beginner | 0 | 0 | 23 | 571 | n/a |
| ecommerce-store | Advanced | 0 | 0 | 4 | 148 | n/a |
| full-stack-web-app | Advanced | 0 | 0 | 1 | 173 | n/a |
| real-estate-website | Intermediate | 0 | 0 | 1 | 151 | n/a |
| social-media-platform | Advanced | 0 | 0 | 7 | 162 | n/a |
| weather-dashboard | Intermediate | 0 | 0 | 37 | 132 | n/a |
| weather-dashboard | Advanced | 0 | 0 | 18 | 137 | n/a |
