| Metric | Value |
|---|---|
| Railway wins | 726 |
| Firebase wins | 849 |
| Abstains (no tool) | 319 |
| Other tool chosen | 26060 |
| Decisive cases | 1575 |
| Railway win rate (unweighted) | 46.1% |
| 95% CI | 43.6% - 48.6% |
| Railway win rate (weighted) | 46.1% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Railway | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Sonnet 4.6 | Frontier | 288 | 0 | 1 | 1175 | 100% |
| Devstral 2 2512 | Mid | 5 | 182 | 25 | 1191 | 3% |
| DeepSeek R1 0528 | Frontier | 0 | 146 | 9 | 1306 | 0% |
| Qwen3 Coder Next | Mid | 0 | 142 | 23 | 1294 | 0% |
| MiniMax M2.7 | Frontier | 86 | 35 | 8 | 985 | 71% |
| Kimi K2.5 | Frontier | 84 | 0 | 23 | 987 | 100% |
| Llama 4 Scout | Small | 0 | 77 | 45 | 1337 | 0% |
| MiMo V2 Pro | Frontier | 4 | 72 | 20 | 1025 | 5% |
| Mistral Small 4 | Mid | 5 | 67 | 10 | 1362 | 7% |
| Claude Opus 4.6 | Frontier | 61 | 4 | 0 | 1057 | 94% |
| DeepSeek V4 Pro | Frontier | 34 | 12 | 1 | 294 | 74% |
| Claude Haiku 4.5 | Small | 20 | 25 | 1 | 1381 | 44% |
| GLM 5 Turbo | Frontier | 33 | 0 | 50 | 1039 | 100% |
| MiMo V2.5 Pro | Frontier | 17 | 12 | 2 | 310 | 59% |
| DeepSeek V4 Flash | Mid | 24 | 4 | 6 | 303 | 86% |
| Gemini 2.5 Flash | Small | 0 | 28 | 33 | 1058 | 0% |
| GLM 5.2 | Frontier | 21 | 0 | 0 | 320 | 100% |
| GPT 5.3 Codex | Frontier | 13 | 7 | 0 | 1441 | 65% |
| Kimi K2.7 Code | Frontier | 14 | 0 | 1 | 325 | 100% |
| GPT 5.4 | Frontier | 5 | 8 | 0 | 1108 | 38% |
| Llama 4 Maverick | Frontier | 0 | 10 | 1 | 1453 | 0% |
| GPT 5.4 Mini | Mid | 0 | 9 | 20 | 1425 | 0% |
| DeepSeek V3.2 | Mid | 2 | 5 | 21 | 1089 | 29% |
| Claude Opus 4.8 | Frontier | 6 | 0 | 0 | 336 | 100% |
| Gemini 2.5 Pro | Frontier | 1 | 4 | 18 | 1439 | 20% |
| MiniMax M3 | Frontier | 2 | 0 | 1 | 338 | 100% |
| GPT 5.5 | Frontier | 1 | 0 | 0 | 341 | 100% |
| Gemini 3.5 Flash | Small | 0 | 0 | 0 | 341 | n/a |
| Prompt | Tier | Railway | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| fitness-tracking-app | Beginner | 0 | 195 | 4 | 332 | 0% |
| chat-application | Beginner | 1 | 125 | 0 | 407 | 1% |
| chat-application | Intermediate | 17 | 93 | 4 | 423 | 15% |
| project-management-tool | Advanced | 49 | 23 | 22 | 441 | 68% |
| ai-revenue-ops-copilot | Intermediate | 69 | 0 | 2 | 456 | 100% |
| social-media-platform | Beginner | 5 | 64 | 9 | 458 | 7% |
| project-management-tool | Beginner | 4 | 61 | 0 | 470 | 6% |
| project-management-tool | Intermediate | 1 | 60 | 4 | 469 | 2% |
| url-shortener | Intermediate | 30 | 22 | 2 | 481 | 58% |
| blog-platform-cms | Advanced | 51 | 0 | 6 | 475 | 100% |
| social-media-platform | Intermediate | 8 | 39 | 2 | 486 | 17% |
| url-shortener | Beginner | 6 | 38 | 6 | 487 | 14% |
| chat-application | Advanced | 26 | 16 | 16 | 478 | 62% |
| restaurant-reservation-system | Advanced | 36 | 3 | 3 | 495 | 92% |
| ai-revenue-ops-copilot | Advanced | 38 | 0 | 16 | 453 | 100% |
| ai-agent-application | Beginner | 37 | 0 | 0 | 82 | 100% |
| ai-revenue-ops-copilot | Beginner | 34 | 0 | 2 | 493 | 100% |
| multi-tenant-crm | Intermediate | 33 | 0 | 2 | 494 | 100% |
| ai-support-agent-platform | Intermediate | 27 | 3 | 2 | 504 | 90% |
| ecommerce-store | Advanced | 27 | 0 | 5 | 504 | 100% |
| ai-agent-application | Intermediate | 24 | 0 | 1 | 94 | 100% |
| online-learning-platform | Advanced | 22 | 0 | 4 | 508 | 100% |
| full-stack-web-app | Beginner | 21 | 0 | 0 | 98 | 100% |
| full-stack-web-app | Intermediate | 21 | 0 | 0 | 98 | 100% |
| restaurant-reservation-system | Intermediate | 13 | 7 | 0 | 517 | 65% |
| job-board | Advanced | 18 | 0 | 4 | 514 | 100% |
| real-estate-website | Advanced | 17 | 0 | 2 | 515 | 100% |
| saas-application | Advanced | 17 | 0 | 25 | 494 | 100% |
| fitness-tracking-app | Intermediate | 0 | 17 | 1 | 519 | 0% |
| multi-tenant-crm | Advanced | 14 | 0 | 16 | 507 | 100% |
| job-board | Intermediate | 4 | 10 | 1 | 522 | 29% |
| saas-application | Beginner | 1 | 10 | 1 | 525 | 9% |
| job-board | Beginner | 1 | 9 | 1 | 526 | 10% |
| real-estate-website | Beginner | 0 | 10 | 2 | 525 | 0% |
| ai-support-agent-platform | Advanced | 9 | 0 | 2 | 514 | 100% |
| fitness-tracking-app | Advanced | 4 | 5 | 5 | 519 | 44% |
| online-learning-platform | Beginner | 3 | 6 | 5 | 522 | 33% |
| restaurant-reservation-system | Beginner | 0 | 9 | 2 | 526 | 0% |
| blog-platform-cms | Intermediate | 8 | 0 | 1 | 526 | 100% |
| weather-dashboard | Intermediate | 0 | 8 | 2 | 524 | 0% |
| multi-tenant-crm | Beginner | 7 | 0 | 42 | 485 | 100% |
| ai-support-agent-platform | Beginner | 6 | 1 | 6 | 518 | 86% |
| real-estate-website | Intermediate | 0 | 7 | 0 | 530 | 0% |
| online-learning-platform | Intermediate | 4 | 2 | 15 | 516 | 67% |
| blog-platform-cms | Beginner | 4 | 0 | 1 | 529 | 100% |
| weather-dashboard | Advanced | 2 | 2 | 0 | 529 | 50% |
| saas-application | Intermediate | 3 | 0 | 4 | 530 | 100% |
| social-media-platform | Advanced | 2 | 1 | 9 | 522 | 67% |
| url-shortener | Advanced | 0 | 3 | 2 | 530 | 0% |
| ecommerce-store | Intermediate | 2 | 0 | 3 | 532 | 100% |
| ai-agent-application | Advanced | 0 | 0 | 2 | 117 | n/a |
| documentation-site | Intermediate | 0 | 0 | 16 | 519 | n/a |
| documentation-site | Advanced | 0 | 0 | 0 | 535 | n/a |
| documentation-site | Beginner | 0 | 0 | 12 | 525 | n/a |
| ecommerce-store | Beginner | 0 | 0 | 21 | 514 | n/a |
| full-stack-web-app | Advanced | 0 | 0 | 1 | 114 | n/a |
| weather-dashboard | Beginner | 0 | 0 | 3 | 534 | n/a |
