| Metric | Value |
|---|---|
| Courier wins | 108 |
| Amazon SNS wins | 158 |
| Abstains (no tool) | 101 |
| Other tool chosen | 6023 |
| Decisive cases | 266 |
| Courier win rate (unweighted) | 40.6% |
| 95% CI | 34.9% - 46.6% |
| Courier win rate (weighted) | 40.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Courier | Amazon SNS | None | Other | A rate |
|---|---|---|---|---|---|---|
| Gemini 2.5 Flash | Small | 3 | 39 | 8 | 213 | 7% |
| Claude Haiku 4.5 | Small | 0 | 36 | 0 | 287 | 0% |
| DeepSeek V3.2 | Mid | 33 | 0 | 12 | 217 | 100% |
| MiMo V2 Pro | Frontier | 0 | 32 | 4 | 228 | 0% |
| GPT 5.3 Codex | Frontier | 11 | 8 | 0 | 317 | 58% |
| Gemini 2.5 Pro | Frontier | 16 | 2 | 2 | 312 | 89% |
| Gemini 3.5 Flash | Small | 17 | 0 | 0 | 55 | 100% |
| Devstral 2 2512 | Mid | 0 | 13 | 0 | 308 | 0% |
| DeepSeek R1 0528 | Frontier | 4 | 4 | 24 | 302 | 50% |
| GPT 5.4 Mini | Mid | 2 | 5 | 8 | 319 | 29% |
| Llama 4 Scout | Small | 0 | 7 | 3 | 321 | 0% |
| DeepSeek V4 Pro | Frontier | 5 | 1 | 0 | 66 | 83% |
| Claude Opus 4.6 | Frontier | 0 | 5 | 0 | 259 | 0% |
| Kimi K2.5 | Frontier | 4 | 0 | 7 | 251 | 100% |
| MiniMax M2.7 | Frontier | 2 | 2 | 14 | 240 | 50% |
| MiMo V2.5 Pro | Frontier | 0 | 4 | 2 | 65 | 0% |
| Claude Sonnet 4.6 | Frontier | 3 | 0 | 0 | 333 | 100% |
| DeepSeek V4 Flash | Mid | 3 | 0 | 0 | 67 | 100% |
| GPT 5.5 | Frontier | 3 | 0 | 0 | 69 | 100% |
| Kimi K2.7 Code | Frontier | 2 | 0 | 0 | 70 | 100% |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 71 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 15 | 249 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 0 | 72 | n/a |
| GPT 5.4 | Frontier | 0 | 0 | 0 | 264 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 1 | 334 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 0 | 72 | n/a |
| Mistral Small 4 | Mid | 0 | 0 | 1 | 327 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 0 | 335 | n/a |
| Prompt | Tier | Courier | Amazon SNS | None | Other | A rate |
|---|---|---|---|---|---|---|
| social-media-platform | Advanced | 37 | 74 | 5 | 418 | 33% |
| chat-application | Advanced | 19 | 32 | 6 | 477 | 37% |
| project-management-tool | Advanced | 8 | 31 | 4 | 478 | 21% |
| restaurant-reservation-system | Advanced | 26 | 2 | 20 | 485 | 93% |
| chat-application | Intermediate | 0 | 12 | 3 | 520 | 0% |
| social-media-platform | Intermediate | 7 | 2 | 1 | 524 | 78% |
| social-media-platform | Beginner | 5 | 4 | 6 | 522 | 56% |
| project-management-tool | Beginner | 2 | 1 | 22 | 509 | 67% |
| restaurant-reservation-system | Intermediate | 2 | 0 | 3 | 532 | 100% |
| project-management-tool | Intermediate | 1 | 0 | 13 | 510 | 100% |
| restaurant-reservation-system | Beginner | 1 | 0 | 4 | 530 | 100% |
| chat-application | Beginner | 0 | 0 | 14 | 518 | n/a |