| Metric | Value |
|---|---|
| AWS wins | 5880 |
| Vercel wins | 16957 |
| Abstains (no tool) | 305 |
| Other tool chosen | 4930 |
| Decisive cases | 22837 |
| AWS win rate (unweighted) | 25.7% |
| 95% CI | 25.2% - 26.3% |
| AWS win rate (weighted) | 25.7% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | AWS | Vercel | None | Other | A rate |
|---|---|---|---|---|---|---|
| GPT 5.4 Mini | Mid | 283 | 1087 | 20 | 70 | 21% |
| Claude Haiku 4.5 | Small | 388 | 942 | 1 | 101 | 29% |
| Llama 4 Maverick | Frontier | 868 | 401 | 1 | 200 | 68% |
| GPT 5.3 Codex | Frontier | 441 | 804 | 0 | 222 | 35% |
| Qwen3 Coder Next | Mid | 132 | 1101 | 21 | 211 | 11% |
| Gemini 2.5 Pro | Frontier | 25 | 1154 | 17 | 272 | 2% |
| DeepSeek R1 0528 | Frontier | 481 | 593 | 9 | 384 | 45% |
| Claude Sonnet 4.6 | Frontier | 90 | 977 | 1 | 402 | 8% |
| GPT 5.4 | Frontier | 223 | 780 | 0 | 67 | 22% |
| Llama 4 Scout | Small | 576 | 407 | 44 | 438 | 59% |
| Mistral Small 4 | Mid | 12 | 957 | 10 | 471 | 1% |
| Claude Opus 4.6 | Frontier | 280 | 685 | 0 | 106 | 29% |
| DeepSeek V3.2 | Mid | 35 | 916 | 20 | 95 | 4% |
| GLM 5 Turbo | Frontier | 57 | 873 | 47 | 94 | 6% |
| Devstral 2 2512 | Mid | 248 | 662 | 24 | 419 | 27% |
| MiMo V2 Pro | Frontier | 512 | 348 | 19 | 191 | 60% |
| Kimi K2.5 | Frontier | 85 | 743 | 20 | 199 | 10% |
| MiniMax M2.7 | Frontier | 101 | 717 | 8 | 237 | 12% |
| Gemini 2.5 Flash | Small | 339 | 469 | 31 | 229 | 42% |
| Kimi K2.7 Code | Frontier | 90 | 276 | 1 | 30 | 25% |
| MiniMax M3 | Frontier | 17 | 345 | 1 | 35 | 5% |
| Claude Opus 4.8 | Frontier | 104 | 254 | 0 | 41 | 29% |
| GLM 5.2 | Frontier | 74 | 277 | 0 | 47 | 21% |
| GPT 5.5 | Frontier | 107 | 232 | 0 | 60 | 32% |
| Gemini 3.5 Flash | Small | 46 | 291 | 0 | 61 | 14% |
| MiMo V2.5 Pro | Frontier | 142 | 185 | 3 | 68 | 43% |
| DeepSeek V4 Flash | Mid | 72 | 231 | 6 | 85 | 24% |
| DeepSeek V4 Pro | Frontier | 52 | 250 | 1 | 95 | 17% |
| Prompt | Tier | AWS | Vercel | None | Other | A rate |
|---|---|---|---|---|---|---|
| weather-dashboard | Beginner | 0 | 533 | 3 | 1 | 0% |
| saas-application | Beginner | 60 | 463 | 1 | 13 | 11% |
| weather-dashboard | Advanced | 42 | 479 | 0 | 13 | 8% |
| real-estate-website | Intermediate | 60 | 458 | 0 | 19 | 12% |
| real-estate-website | Beginner | 12 | 505 | 2 | 18 | 2% |
| saas-application | Intermediate | 66 | 450 | 3 | 18 | 13% |
| fitness-tracking-app | Intermediate | 59 | 455 | 1 | 22 | 11% |
| restaurant-reservation-system | Beginner | 36 | 476 | 2 | 23 | 7% |
| weather-dashboard | Intermediate | 0 | 508 | 3 | 23 | 0% |
| job-board | Intermediate | 46 | 456 | 1 | 34 | 9% |
| job-board | Beginner | 35 | 462 | 1 | 39 | 7% |
| online-learning-platform | Intermediate | 68 | 421 | 14 | 34 | 14% |
| documentation-site | Advanced | 4 | 483 | 0 | 48 | 1% |
| ai-support-agent-platform | Beginner | 48 | 438 | 6 | 39 | 10% |
| real-estate-website | Advanced | 233 | 245 | 2 | 54 | 49% |
| online-learning-platform | Beginner | 45 | 433 | 5 | 54 | 9% |
| documentation-site | Beginner | 0 | 478 | 12 | 47 | 0% |
| ai-support-agent-platform | Advanced | 227 | 250 | 2 | 47 | 48% |
| ai-support-agent-platform | Intermediate | 86 | 387 | 2 | 61 | 18% |
| fitness-tracking-app | Advanced | 301 | 171 | 4 | 57 | 64% |
| restaurant-reservation-system | Intermediate | 72 | 399 | 0 | 66 | 15% |
| online-learning-platform | Advanced | 308 | 158 | 4 | 64 | 66% |
| saas-application | Advanced | 290 | 175 | 25 | 46 | 62% |
| url-shortener | Beginner | 13 | 452 | 6 | 66 | 3% |
| job-board | Advanced | 292 | 170 | 4 | 70 | 63% |
| ecommerce-store | Advanced | 355 | 98 | 3 | 80 | 78% |
| social-media-platform | Intermediate | 90 | 363 | 2 | 80 | 20% |
| project-management-tool | Beginner | 12 | 435 | 0 | 88 | 3% |
| multi-tenant-crm | Beginner | 68 | 374 | 41 | 51 | 15% |
| social-media-platform | Beginner | 55 | 387 | 9 | 85 | 12% |
| ecommerce-store | Intermediate | 29 | 410 | 2 | 96 | 7% |
| documentation-site | Intermediate | 0 | 439 | 16 | 80 | 0% |
| project-management-tool | Intermediate | 8 | 430 | 3 | 93 | 2% |
| multi-tenant-crm | Advanced | 373 | 51 | 15 | 98 | 88% |
| blog-platform-cms | Intermediate | 14 | 400 | 1 | 120 | 3% |
| restaurant-reservation-system | Advanced | 310 | 103 | 3 | 121 | 75% |
| url-shortener | Intermediate | 15 | 387 | 2 | 132 | 4% |
| blog-platform-cms | Advanced | 213 | 185 | 6 | 128 | 54% |
| social-media-platform | Advanced | 302 | 94 | 8 | 130 | 76% |
| ai-revenue-ops-copilot | Beginner | 84 | 312 | 2 | 131 | 21% |
| multi-tenant-crm | Intermediate | 67 | 327 | 2 | 134 | 17% |
| chat-application | Beginner | 33 | 352 | 0 | 147 | 9% |
| chat-application | Intermediate | 51 | 322 | 4 | 160 | 14% |
| ecommerce-store | Beginner | 11 | 346 | 20 | 158 | 3% |
| project-management-tool | Advanced | 146 | 203 | 20 | 166 | 42% |
| chat-application | Advanced | 274 | 67 | 16 | 179 | 80% |
| ai-revenue-ops-copilot | Intermediate | 150 | 177 | 2 | 198 | 46% |
| ai-revenue-ops-copilot | Advanced | 214 | 109 | 14 | 170 | 66% |
| url-shortener | Advanced | 257 | 47 | 2 | 229 | 85% |
| fitness-tracking-app | Beginner | 1 | 267 | 4 | 259 | 0% |
| blog-platform-cms | Beginner | 1 | 260 | 1 | 272 | 0% |
| ai-agent-application | Advanced | 115 | 0 | 2 | 21 | 100% |
| full-stack-web-app | Advanced | 102 | 10 | 1 | 21 | 91% |
| ai-agent-application | Intermediate | 68 | 4 | 1 | 65 | 94% |
| full-stack-web-app | Intermediate | 27 | 29 | 0 | 82 | 48% |
| full-stack-web-app | Beginner | 0 | 52 | 0 | 86 | 0% |
| ai-agent-application | Beginner | 32 | 12 | 0 | 94 | 73% |
