| Metric | Value |
|---|---|
| AWS S3 wins | 8804 |
| Cloudflare R2 wins | 1740 |
| Abstains (no tool) | 248 |
| Other tool chosen | 5009 |
| Decisive cases | 10544 |
| AWS S3 win rate (unweighted) | 83.5% |
| 95% CI | 82.8% - 84.2% |
| AWS S3 win rate (weighted) | 83.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | AWS S3 | Cloudflare R2 | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 210 | 179 | 32 | 404 | 54% |
| DeepSeek Pro 4–4 0813 | Frontier | 69 | 25 | 1 | 91 | 73% |
| DeepSeek R1 | Frontier | 595 | 2 | 5 | 224 | 100% |
| Devstral | Mid | 389 | 0 | 37 | 357 | 100% |
| Gemini Flash 2.5–3.8 | Small | 669 | 2 | 44 | 113 | 100% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 457 | 168 | 28 | 174 | 73% |
| GLM 5 Turbo–5.3 | Frontier | 467 | 217 | 19 | 125 | 68% |
| GPT 5.4–6 Astra | Frontier | 461 | 82 | 10 | 273 | 85% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 432 | 36 | 4 | 354 | 92% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 506 | 50 | 9 | 256 | 91% |
| Haiku | Small | 683 | 0 | 0 | 139 | 100% |
| Kimi 2.5–3 | Frontier | 289 | 273 | 13 | 250 | 51% |
| Llama Maverick | Frontier | 809 | 0 | 3 | 16 | 100% |
| Llama Scout | Small | 710 | 0 | 26 | 89 | 100% |
| MiMo Pro 2–2.6 | Frontier | 572 | 16 | 6 | 230 | 97% |
| MiniMax M 2.7–3 | Frontier | 399 | 84 | 4 | 339 | 83% |
| Mistral Small | Mid | 232 | 336 | 0 | 226 | 41% |
| Opus 4.6–5.5 | Frontier | 369 | 91 | 2 | 365 | 80% |
| Qwen Coder | Mid | 262 | 109 | 4 | 451 | 71% |
| Sonnet 4.6–5.5 | Frontier | 224 | 70 | 1 | 533 | 76% |
| Prompt | Tier | AWS S3 | Cloudflare R2 | None | Other | A rate |
|---|---|---|---|---|---|---|
| ecommerce-store | Advanced | 559 | 30 | 1 | 5 | 95% |
| job-board | Advanced | 568 | 10 | 1 | 11 | 98% |
| social-media-platform | Advanced | 405 | 140 | 5 | 42 | 74% |
| chat-application | Advanced | 452 | 84 | 5 | 51 | 84% |
| project-management-tool | Advanced | 429 | 100 | 4 | 59 | 81% |
| job-board | Intermediate | 415 | 77 | 0 | 104 | 84% |
| online-learning-platform | Advanced | 397 | 83 | 4 | 98 | 83% |
| real-estate-website | Advanced | 392 | 86 | 2 | 114 | 82% |
| online-learning-platform | Intermediate | 417 | 59 | 1 | 119 | 88% |
| social-media-platform | Intermediate | 333 | 78 | 1 | 184 | 81% |
| ecommerce-store | Intermediate | 338 | 54 | 17 | 183 | 86% |
| job-board | Beginner | 320 | 60 | 0 | 216 | 84% |
| online-learning-platform | Beginner | 243 | 81 | 28 | 240 | 75% |
| chat-application | Intermediate | 220 | 78 | 4 | 294 | 74% |
| chat-application | Beginner | 236 | 52 | 21 | 285 | 82% |
| real-estate-website | Intermediate | 212 | 64 | 0 | 320 | 77% |
| social-media-platform | Beginner | 154 | 122 | 1 | 319 | 56% |
| project-management-tool | Beginner | 208 | 37 | 2 | 346 | 85% |
| project-management-tool | Intermediate | 203 | 42 | 1 | 346 | 83% |
| ecommerce-store | Beginner | 183 | 51 | 83 | 275 | 78% |
| job-board | Advanced | 167 | 2 | 0 | 2 | 99% |
| social-media-platform | Advanced | 136 | 31 | 1 | 2 | 81% |
| ecommerce-store | Advanced | 141 | 7 | 1 | 0 | 95% |
| real-estate-website | Advanced | 124 | 23 | 0 | 22 | 84% |
| online-learning-platform | Advanced | 133 | 12 | 0 | 5 | 92% |
| online-learning-platform | Intermediate | 127 | 11 | 0 | 14 | 92% |
| project-management-tool | Advanced | 127 | 10 | 0 | 13 | 93% |
| job-board | Intermediate | 117 | 20 | 2 | 13 | 85% |
| ecommerce-store | Intermediate | 119 | 17 | 0 | 33 | 88% |
| chat-application | Advanced | 120 | 12 | 2 | 18 | 91% |
| job-board | Beginner | 98 | 23 | 1 | 49 | 81% |
| real-estate-website | Beginner | 89 | 27 | 4 | 474 | 77% |
| social-media-platform | Intermediate | 97 | 15 | 1 | 39 | 87% |
| online-learning-platform | Beginner | 64 | 40 | 7 | 58 | 62% |
| chat-application | Intermediate | 73 | 15 | 0 | 82 | 83% |
| project-management-tool | Beginner | 76 | 10 | 3 | 63 | 88% |
| project-management-tool | Intermediate | 82 | 2 | 1 | 67 | 98% |
| real-estate-website | Intermediate | 69 | 11 | 1 | 71 | 86% |
| social-media-platform | Beginner | 44 | 30 | 0 | 97 | 59% |
| chat-application | Beginner | 51 | 13 | 2 | 101 | 80% |
| ecommerce-store | Beginner | 38 | 14 | 32 | 67 | 73% |
| real-estate-website | Beginner | 28 | 7 | 9 | 108 | 80% |
