| Metric | Value |
|---|---|
| Vercel wins | 16957 |
| AWS wins | 5880 |
| Abstains (no tool) | 305 |
| Other tool chosen | 4930 |
| Decisive cases | 22837 |
| Vercel win rate (unweighted) | 74.3% |
| 95% CI | 73.7% - 74.8% |
| Vercel win rate (weighted) | 74.3% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Vercel | AWS | None | Other | A rate |
|---|---|---|---|---|---|---|
| GPT 5.4 Mini | Mid | 1087 | 283 | 20 | 70 | 79% |
| Claude Haiku 4.5 | Small | 942 | 388 | 1 | 101 | 71% |
| Llama 4 Maverick | Frontier | 401 | 868 | 1 | 200 | 32% |
| GPT 5.3 Codex | Frontier | 804 | 441 | 0 | 222 | 65% |
| Qwen3 Coder Next | Mid | 1101 | 132 | 21 | 211 | 89% |
| Gemini 2.5 Pro | Frontier | 1154 | 25 | 17 | 272 | 98% |
| DeepSeek R1 0528 | Frontier | 593 | 481 | 9 | 384 | 55% |
| Claude Sonnet 4.6 | Frontier | 977 | 90 | 1 | 402 | 92% |
| GPT 5.4 | Frontier | 780 | 223 | 0 | 67 | 78% |
| Llama 4 Scout | Small | 407 | 576 | 44 | 438 | 41% |
| Mistral Small 4 | Mid | 957 | 12 | 10 | 471 | 99% |
| Claude Opus 4.6 | Frontier | 685 | 280 | 0 | 106 | 71% |
| DeepSeek V3.2 | Mid | 916 | 35 | 20 | 95 | 96% |
| GLM 5 Turbo | Frontier | 873 | 57 | 47 | 94 | 94% |
| Devstral 2 2512 | Mid | 662 | 248 | 24 | 419 | 73% |
| MiMo V2 Pro | Frontier | 348 | 512 | 19 | 191 | 40% |
| Kimi K2.5 | Frontier | 743 | 85 | 20 | 199 | 90% |
| MiniMax M2.7 | Frontier | 717 | 101 | 8 | 237 | 88% |
| Gemini 2.5 Flash | Small | 469 | 339 | 31 | 229 | 58% |
| Kimi K2.7 Code | Frontier | 276 | 90 | 1 | 30 | 75% |
| MiniMax M3 | Frontier | 345 | 17 | 1 | 35 | 95% |
| Claude Opus 4.8 | Frontier | 254 | 104 | 0 | 41 | 71% |
| GLM 5.2 | Frontier | 277 | 74 | 0 | 47 | 79% |
| GPT 5.5 | Frontier | 232 | 107 | 0 | 60 | 68% |
| Gemini 3.5 Flash | Small | 291 | 46 | 0 | 61 | 86% |
| MiMo V2.5 Pro | Frontier | 185 | 142 | 3 | 68 | 57% |
| DeepSeek V4 Flash | Mid | 231 | 72 | 6 | 85 | 76% |
| DeepSeek V4 Pro | Frontier | 250 | 52 | 1 | 95 | 83% |
| Prompt | Tier | Vercel | AWS | None | Other | A rate |
|---|---|---|---|---|---|---|
| weather-dashboard | Beginner | 533 | 0 | 3 | 1 | 100% |
| saas-application | Beginner | 463 | 60 | 1 | 13 | 89% |
| weather-dashboard | Advanced | 479 | 42 | 0 | 13 | 92% |
| real-estate-website | Intermediate | 458 | 60 | 0 | 19 | 88% |
| real-estate-website | Beginner | 505 | 12 | 2 | 18 | 98% |
| saas-application | Intermediate | 450 | 66 | 3 | 18 | 87% |
| fitness-tracking-app | Intermediate | 455 | 59 | 1 | 22 | 89% |
| restaurant-reservation-system | Beginner | 476 | 36 | 2 | 23 | 93% |
| weather-dashboard | Intermediate | 508 | 0 | 3 | 23 | 100% |
| job-board | Intermediate | 456 | 46 | 1 | 34 | 91% |
| job-board | Beginner | 462 | 35 | 1 | 39 | 93% |
| online-learning-platform | Intermediate | 421 | 68 | 14 | 34 | 86% |
| documentation-site | Advanced | 483 | 4 | 0 | 48 | 99% |
| ai-support-agent-platform | Beginner | 438 | 48 | 6 | 39 | 90% |
| documentation-site | Beginner | 478 | 0 | 12 | 47 | 100% |
| online-learning-platform | Beginner | 433 | 45 | 5 | 54 | 91% |
| real-estate-website | Advanced | 245 | 233 | 2 | 54 | 51% |
| ai-support-agent-platform | Advanced | 250 | 227 | 2 | 47 | 52% |
| ai-support-agent-platform | Intermediate | 387 | 86 | 2 | 61 | 82% |
| fitness-tracking-app | Advanced | 171 | 301 | 4 | 57 | 36% |
| restaurant-reservation-system | Intermediate | 399 | 72 | 0 | 66 | 85% |
| online-learning-platform | Advanced | 158 | 308 | 4 | 64 | 34% |
| url-shortener | Beginner | 452 | 13 | 6 | 66 | 97% |
| saas-application | Advanced | 175 | 290 | 25 | 46 | 38% |
| job-board | Advanced | 170 | 292 | 4 | 70 | 37% |
| social-media-platform | Intermediate | 363 | 90 | 2 | 80 | 80% |
| ecommerce-store | Advanced | 98 | 355 | 3 | 80 | 22% |
| project-management-tool | Beginner | 435 | 12 | 0 | 88 | 97% |
| social-media-platform | Beginner | 387 | 55 | 9 | 85 | 88% |
| multi-tenant-crm | Beginner | 374 | 68 | 41 | 51 | 85% |
| documentation-site | Intermediate | 439 | 0 | 16 | 80 | 100% |
| ecommerce-store | Intermediate | 410 | 29 | 2 | 96 | 93% |
| project-management-tool | Intermediate | 430 | 8 | 3 | 93 | 98% |
| multi-tenant-crm | Advanced | 51 | 373 | 15 | 98 | 12% |
| blog-platform-cms | Intermediate | 400 | 14 | 1 | 120 | 97% |
| restaurant-reservation-system | Advanced | 103 | 310 | 3 | 121 | 25% |
| url-shortener | Intermediate | 387 | 15 | 2 | 132 | 96% |
| blog-platform-cms | Advanced | 185 | 213 | 6 | 128 | 46% |
| ai-revenue-ops-copilot | Beginner | 312 | 84 | 2 | 131 | 79% |
| social-media-platform | Advanced | 94 | 302 | 8 | 130 | 24% |
| multi-tenant-crm | Intermediate | 327 | 67 | 2 | 134 | 83% |
| chat-application | Beginner | 352 | 33 | 0 | 147 | 91% |
| chat-application | Intermediate | 322 | 51 | 4 | 160 | 86% |
| ecommerce-store | Beginner | 346 | 11 | 20 | 158 | 97% |
| project-management-tool | Advanced | 203 | 146 | 20 | 166 | 58% |
| chat-application | Advanced | 67 | 274 | 16 | 179 | 20% |
| ai-revenue-ops-copilot | Intermediate | 177 | 150 | 2 | 198 | 54% |
| ai-revenue-ops-copilot | Advanced | 109 | 214 | 14 | 170 | 34% |
| url-shortener | Advanced | 47 | 257 | 2 | 229 | 15% |
| fitness-tracking-app | Beginner | 267 | 1 | 4 | 259 | 100% |
| blog-platform-cms | Beginner | 260 | 1 | 1 | 272 | 100% |
| ai-agent-application | Advanced | 0 | 115 | 2 | 21 | 0% |
| full-stack-web-app | Advanced | 10 | 102 | 1 | 21 | 9% |
| ai-agent-application | Intermediate | 4 | 68 | 1 | 65 | 6% |
| full-stack-web-app | Intermediate | 29 | 27 | 0 | 82 | 52% |
| full-stack-web-app | Beginner | 52 | 0 | 0 | 86 | 100% |
| ai-agent-application | Beginner | 12 | 32 | 0 | 94 | 27% |