| Metric | Value |
|---|---|
| Mailgun wins | 224 |
| Postmark wins | 613 |
| Abstains (no tool) | 110 |
| Other tool chosen | 7407 |
| Decisive cases | 837 |
| Mailgun win rate (unweighted) | 26.8% |
| 95% CI | 23.9% - 29.9% |
| Mailgun win rate (weighted) | 26.8% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Mailgun | Postmark | None | Other | A rate |
|---|---|---|---|---|---|---|
| GPT 5.3 Codex | Frontier | 1 | 143 | 1 | 296 | 1% |
| Claude Opus 4.6 | Frontier | 40 | 73 | 0 | 328 | 35% |
| Mistral Small 4 | Mid | 3 | 107 | 0 | 328 | 3% |
| Gemini 2.5 Pro | Frontier | 25 | 78 | 9 | 329 | 24% |
| Llama 4 Maverick | Frontier | 66 | 0 | 0 | 375 | 100% |
| Claude Sonnet 4.6 | Frontier | 21 | 37 | 0 | 383 | 36% |
| Qwen3 Coder Next | Mid | 0 | 54 | 8 | 376 | 0% |
| GPT 5.4 Mini | Mid | 0 | 42 | 5 | 394 | 0% |
| Devstral 2 2512 | Mid | 14 | 25 | 0 | 400 | 36% |
| Gemini 2.5 Flash | Small | 14 | 22 | 0 | 405 | 39% |
| MiMo V2 Pro | Frontier | 13 | 5 | 2 | 421 | 72% |
| Llama 4 Scout | Small | 13 | 0 | 22 | 404 | 100% |
| MiniMax M2.7 | Frontier | 7 | 6 | 7 | 419 | 54% |
| GPT 5.4 | Frontier | 5 | 7 | 1 | 428 | 42% |
| DeepSeek V3.2 | Mid | 1 | 6 | 4 | 424 | 14% |
| Kimi K2.5 | Frontier | 0 | 6 | 13 | 417 | 0% |
| Claude Haiku 4.5 | Small | 1 | 0 | 14 | 424 | 100% |
| DeepSeek R1 0528 | Frontier | 0 | 1 | 5 | 435 | 0% |
| GLM 5 Turbo | Frontier | 0 | 1 | 19 | 421 | 0% |
| Prompt | Tier | Mailgun | Postmark | None | Other | A rate |
|---|---|---|---|---|---|---|
| blog-platform-cms | Beginner | 120 | 2 | 26 | 244 | 98% |
| saas-application | Advanced | 0 | 86 | 24 | 288 | 0% |
| blog-platform-cms | Intermediate | 79 | 6 | 1 | 313 | 93% |
| online-learning-platform | Advanced | 1 | 72 | 7 | 319 | 1% |
| ecommerce-store | Advanced | 13 | 56 | 2 | 328 | 19% |
| saas-application | Beginner | 0 | 67 | 3 | 329 | 0% |
| job-board | Advanced | 0 | 63 | 0 | 336 | 0% |
| blog-platform-cms | Advanced | 11 | 51 | 3 | 334 | 18% |
| restaurant-reservation-system | Advanced | 0 | 36 | 3 | 360 | 0% |
| saas-application | Intermediate | 0 | 34 | 4 | 361 | 0% |
| multi-tenant-crm | Advanced | 0 | 31 | 3 | 365 | 0% |
| restaurant-reservation-system | Beginner | 0 | 21 | 8 | 370 | 0% |
| ecommerce-store | Intermediate | 0 | 20 | 1 | 378 | 0% |
| ecommerce-store | Beginner | 0 | 18 | 12 | 367 | 0% |
| multi-tenant-crm | Intermediate | 0 | 17 | 1 | 375 | 0% |
| restaurant-reservation-system | Intermediate | 0 | 13 | 9 | 377 | 0% |
| online-learning-platform | Beginner | 0 | 12 | 0 | 386 | 0% |
| job-board | Beginner | 0 | 3 | 0 | 396 | 0% |
| online-learning-platform | Intermediate | 0 | 3 | 1 | 394 | 0% |
| multi-tenant-crm | Beginner | 0 | 2 | 2 | 388 | 0% |
| job-board | Intermediate | 0 | 0 | 0 | 399 | n/a |