Leading: Ghost (50.9%)
| Metric | Value |
|---|---|
| Google Cloud Platform (GCP) wins | 173 |
| Ghost wins | 179 |
| Abstains (no tool) | 305 |
| Other tool chosen | 27415 |
| Decisive cases | 352 |
| Google Cloud Platform (GCP) win rate (unweighted) | 49.1% |
| 95% CI | 44.0% - 54.4% |
| Google Cloud Platform (GCP) win rate (weighted) | 49.1% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Google Cloud Platform (GCP) | Ghost | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 33 | 20 | 24 | 1276 | 62% |
| Gemini 2.5 Flash | Small | 46 | 0 | 31 | 991 | 100% |
| Gemini 2.5 Pro | Frontier | 13 | 26 | 17 | 1412 | 33% |
| Claude Sonnet 4.6 | Frontier | 0 | 28 | 1 | 1441 | 0% |
| GLM 5 Turbo | Frontier | 1 | 25 | 47 | 998 | 4% |
| Llama 4 Scout | Small | 25 | 0 | 44 | 1396 | 100% |
| Claude Opus 4.6 | Frontier | 0 | 21 | 0 | 1050 | 0% |
| MiniMax M2.7 | Frontier | 16 | 4 | 8 | 1035 | 80% |
| Llama 4 Maverick | Frontier | 10 | 7 | 1 | 1452 | 59% |
| MiMo V2 Pro | Frontier | 3 | 14 | 19 | 1034 | 18% |
| DeepSeek R1 0528 | Frontier | 9 | 0 | 9 | 1449 | 100% |
| DeepSeek V4 Flash | Mid | 2 | 6 | 6 | 380 | 25% |
| DeepSeek V4 Pro | Frontier | 1 | 6 | 1 | 390 | 14% |
| GPT 5.4 | Frontier | 0 | 6 | 0 | 1064 | 0% |
| GPT 5.3 Codex | Frontier | 3 | 2 | 0 | 1462 | 60% |
| GPT 5.5 | Frontier | 1 | 4 | 0 | 394 | 20% |
| Gemini 3.5 Flash | Small | 0 | 5 | 0 | 393 | 0% |
| Mistral Small 4 | Mid | 4 | 0 | 10 | 1436 | 100% |
| GPT 5.4 Mini | Mid | 3 | 0 | 20 | 1437 | 100% |
| MiMo V2.5 Pro | Frontier | 3 | 0 | 3 | 392 | 100% |
| GLM 5.2 | Frontier | 0 | 2 | 0 | 396 | 0% |
| DeepSeek V3.2 | Mid | 0 | 1 | 20 | 1045 | 0% |
| Kimi K2.7 Code | Frontier | 0 | 1 | 1 | 395 | 0% |
| Qwen3 Coder Next | Mid | 0 | 1 | 21 | 1443 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 1 | 1431 | n/a |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 399 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 20 | 1027 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 1 | 397 | n/a |
| Prompt | Tier | Google Cloud Platform (GCP) | Ghost | None | Other | A rate |
|---|---|---|---|---|---|---|
| blog-platform-cms | Beginner | 0 | 163 | 1 | 370 | 0% |
| social-media-platform | Advanced | 29 | 0 | 8 | 497 | 100% |
| ai-revenue-ops-copilot | Beginner | 28 | 0 | 2 | 499 | 100% |
| chat-application | Intermediate | 19 | 0 | 4 | 514 | 100% |
| chat-application | Advanced | 17 | 0 | 16 | 503 | 100% |
| ai-revenue-ops-copilot | Advanced | 16 | 0 | 14 | 477 | 100% |
| blog-platform-cms | Intermediate | 0 | 15 | 1 | 519 | 0% |
| fitness-tracking-app | Beginner | 11 | 0 | 4 | 516 | 100% |
| ai-support-agent-platform | Advanced | 8 | 0 | 2 | 516 | 100% |
| fitness-tracking-app | Advanced | 7 | 0 | 4 | 522 | 100% |
| url-shortener | Advanced | 5 | 0 | 2 | 528 | 100% |
| ai-agent-application | Advanced | 4 | 0 | 2 | 132 | 100% |
| project-management-tool | Advanced | 4 | 0 | 20 | 511 | 100% |
| restaurant-reservation-system | Advanced | 4 | 0 | 3 | 530 | 100% |
| social-media-platform | Intermediate | 4 | 0 | 2 | 529 | 100% |
| chat-application | Beginner | 3 | 0 | 0 | 529 | 100% |
| ecommerce-store | Advanced | 2 | 0 | 3 | 531 | 100% |
| online-learning-platform | Advanced | 2 | 0 | 4 | 528 | 100% |
| restaurant-reservation-system | Intermediate | 2 | 0 | 0 | 535 | 100% |
| blog-platform-cms | Advanced | 1 | 1 | 6 | 524 | 50% |
| ai-agent-application | Intermediate | 1 | 0 | 1 | 136 | 100% |
| ai-revenue-ops-copilot | Intermediate | 1 | 0 | 2 | 524 | 100% |
| full-stack-web-app | Advanced | 1 | 0 | 1 | 132 | 100% |
| job-board | Advanced | 1 | 0 | 4 | 531 | 100% |
| multi-tenant-crm | Advanced | 1 | 0 | 15 | 521 | 100% |
| saas-application | Advanced | 1 | 0 | 25 | 510 | 100% |
| social-media-platform | Beginner | 1 | 0 | 9 | 526 | 100% |
| ai-agent-application | Beginner | 0 | 0 | 0 | 138 | n/a |
| ai-support-agent-platform | Beginner | 0 | 0 | 6 | 525 | n/a |
| ai-support-agent-platform | Intermediate | 0 | 0 | 2 | 534 | n/a |
| documentation-site | Advanced | 0 | 0 | 0 | 535 | n/a |
| documentation-site | Intermediate | 0 | 0 | 16 | 519 | n/a |
| documentation-site | Beginner | 0 | 0 | 12 | 525 | n/a |
| ecommerce-store | Intermediate | 0 | 0 | 2 | 535 | n/a |
| ecommerce-store | Beginner | 0 | 0 | 20 | 515 | n/a |
| fitness-tracking-app | Intermediate | 0 | 0 | 1 | 536 | n/a |
| full-stack-web-app | Beginner | 0 | 0 | 0 | 138 | n/a |
| full-stack-web-app | Intermediate | 0 | 0 | 0 | 138 | n/a |
| job-board | Beginner | 0 | 0 | 1 | 536 | n/a |
| job-board | Intermediate | 0 | 0 | 1 | 536 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 41 | 493 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 2 | 528 | n/a |
| online-learning-platform | Intermediate | 0 | 0 | 14 | 523 | n/a |
| online-learning-platform | Beginner | 0 | 0 | 5 | 532 | n/a |
| project-management-tool | Beginner | 0 | 0 | 0 | 535 | n/a |
| project-management-tool | Intermediate | 0 | 0 | 3 | 531 | n/a |
| real-estate-website | Advanced | 0 | 0 | 2 | 532 | n/a |
| real-estate-website | Beginner | 0 | 0 | 2 | 535 | n/a |
| real-estate-website | Intermediate | 0 | 0 | 0 | 537 | n/a |
| restaurant-reservation-system | Beginner | 0 | 0 | 2 | 535 | n/a |
| saas-application | Beginner | 0 | 0 | 1 | 536 | n/a |
| saas-application | Intermediate | 0 | 0 | 3 | 534 | n/a |
| url-shortener | Beginner | 0 | 0 | 6 | 531 | n/a |
| url-shortener | Intermediate | 0 | 0 | 2 | 534 | n/a |
| weather-dashboard | Beginner | 0 | 0 | 3 | 534 | n/a |
| weather-dashboard | Intermediate | 0 | 0 | 3 | 531 | n/a |
| weather-dashboard | Advanced | 0 | 0 | 0 | 534 | n/a |
