| Metric | Value |
|---|---|
| Courier wins | 142 |
| Amazon SNS wins | 217 |
| Abstains (no tool) | 146 |
| Other tool chosen | 8495 |
| Decisive cases | 359 |
| Courier win rate (unweighted) | 39.6% |
| 95% CI | 34.6% - 44.7% |
| Courier win rate (weighted) | 39.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Courier | Amazon SNS | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 44 | 2 | 20 | 403 | 96% |
| DeepSeek Pro 4–4 0813 | Frontier | 6 | 2 | 0 | 100 | 75% |
| DeepSeek R1 | Frontier | 6 | 5 | 34 | 425 | 55% |
| Devstral | Mid | 0 | 13 | 0 | 433 | 0% |
| Gemini Flash 2.5–3.8 | Small | 24 | 54 | 12 | 381 | 31% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 23 | 3 | 2 | 440 | 88% |
| GLM 5 Turbo–5.3 | Frontier | 0 | 2 | 18 | 452 | 0% |
| GPT 5.4–6 Astra | Frontier | 5 | 0 | 1 | 466 | 100% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 15 | 9 | 1 | 447 | 63% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 2 | 6 | 16 | 446 | 25% |
| Haiku | Small | 0 | 52 | 1 | 406 | 0% |
| Kimi 2.5–3 | Frontier | 8 | 0 | 8 | 454 | 100% |
| Llama Maverick | Frontier | 0 | 0 | 1 | 471 | n/a |
| Llama Scout | Small | 0 | 16 | 4 | 447 | 0% |
| MiMo Pro 2–2.6 | Frontier | 0 | 40 | 7 | 424 | 0% |
| MiniMax M 2.7–3 | Frontier | 2 | 3 | 19 | 442 | 40% |
| Mistral Small | Mid | 0 | 0 | 1 | 460 | n/a |
| Opus 4.6–5.5 | Frontier | 0 | 10 | 0 | 461 | 0% |
| Qwen Coder | Mid | 0 | 0 | 1 | 471 | n/a |
| Sonnet 4.6–5.5 | Frontier | 7 | 0 | 0 | 466 | 100% |
| Prompt | Tier | Courier | Amazon SNS | None | Other | A rate |
|---|---|---|---|---|---|---|
| social-media-platform | Advanced | 43 | 80 | 6 | 465 | 35% |
| chat-application | Advanced | 20 | 37 | 6 | 530 | 35% |
| project-management-tool | Advanced | 9 | 33 | 5 | 532 | 21% |
| social-media-platform | Advanced | 12 | 22 | 1 | 135 | 35% |
| restaurant-reservation-system | Advanced | 26 | 2 | 20 | 544 | 93% |
| chat-application | Advanced | 3 | 14 | 3 | 132 | 18% |
| chat-application | Intermediate | 0 | 12 | 3 | 577 | 0% |
| project-management-tool | Advanced | 4 | 7 | 2 | 137 | 36% |
| social-media-platform | Intermediate | 7 | 3 | 1 | 582 | 70% |
| social-media-platform | Beginner | 6 | 4 | 7 | 579 | 60% |
| restaurant-reservation-system | Advanced | 6 | 1 | 4 | 139 | 86% |
| project-management-tool | Beginner | 2 | 1 | 23 | 567 | 67% |
| restaurant-reservation-system | Intermediate | 2 | 0 | 3 | 591 | 100% |
| project-management-tool | Intermediate | 1 | 0 | 16 | 564 | 100% |
| restaurant-reservation-system | Beginner | 1 | 0 | 4 | 589 | 100% |
| social-media-platform | Intermediate | 0 | 1 | 1 | 148 | 0% |
| chat-application | Intermediate | 0 | 0 | 0 | 170 | n/a |
| chat-application | Beginner | 0 | 0 | 15 | 576 | n/a |
| chat-application | Beginner | 0 | 0 | 2 | 165 | n/a |
| project-management-tool | Intermediate | 0 | 0 | 6 | 146 | n/a |
| project-management-tool | Beginner | 0 | 0 | 11 | 140 | n/a |
| restaurant-reservation-system | Intermediate | 0 | 0 | 2 | 169 | n/a |
| restaurant-reservation-system | Beginner | 0 | 0 | 2 | 150 | n/a |
| social-media-platform | Beginner | 0 | 0 | 3 | 168 | n/a |