| Metric | Value |
|---|---|
| Novu wins | 658 |
| SendGrid wins | 629 |
| Abstains (no tool) | 146 |
| Other tool chosen | 7567 |
| Decisive cases | 1287 |
| Novu win rate (unweighted) | 51.1% |
| 95% CI | 48.4% - 53.9% |
| Novu win rate (weighted) | 51.1% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Novu | SendGrid | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 25 | 22 | 20 | 402 | 53% |
| DeepSeek Pro 4–4 0813 | Frontier | 14 | 0 | 0 | 94 | 100% |
| DeepSeek R1 | Frontier | 1 | 48 | 34 | 387 | 2% |
| Devstral | Mid | 0 | 51 | 0 | 395 | 0% |
| Gemini Flash 2.5–3.8 | Small | 15 | 51 | 12 | 393 | 23% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 89 | 7 | 2 | 370 | 93% |
| GLM 5 Turbo–5.3 | Frontier | 188 | 0 | 18 | 266 | 100% |
| GPT 5.4–6 Astra | Frontier | 33 | 28 | 1 | 410 | 54% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 78 | 2 | 1 | 391 | 98% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 5 | 103 | 16 | 346 | 5% |
| Haiku | Small | 0 | 98 | 1 | 360 | 0% |
| Kimi 2.5–3 | Frontier | 128 | 0 | 8 | 334 | 100% |
| Llama Maverick | Frontier | 2 | 2 | 1 | 467 | 50% |
| Llama Scout | Small | 0 | 114 | 4 | 349 | 0% |
| MiMo Pro 2–2.6 | Frontier | 19 | 22 | 7 | 423 | 46% |
| MiniMax M 2.7–3 | Frontier | 7 | 5 | 19 | 435 | 58% |
| Mistral Small | Mid | 0 | 32 | 1 | 428 | 0% |
| Opus 4.6–5.5 | Frontier | 42 | 3 | 0 | 426 | 93% |
| Qwen Coder | Mid | 0 | 41 | 1 | 430 | 0% |
| Sonnet 4.6–5.5 | Frontier | 12 | 0 | 0 | 461 | 100% |
| Prompt | Tier | Novu | SendGrid | None | Other | A rate |
|---|---|---|---|---|---|---|
| project-management-tool | Beginner | 114 | 114 | 23 | 342 | 50% |
| project-management-tool | Intermediate | 140 | 54 | 16 | 371 | 72% |
| project-management-tool | Advanced | 49 | 84 | 5 | 441 | 37% |
| social-media-platform | Intermediate | 57 | 60 | 1 | 475 | 49% |
| social-media-platform | Advanced | 40 | 65 | 6 | 483 | 38% |
| social-media-platform | Beginner | 42 | 34 | 7 | 513 | 55% |
| project-management-tool | Beginner | 22 | 42 | 11 | 76 | 34% |
| project-management-tool | Intermediate | 37 | 17 | 6 | 92 | 69% |
| social-media-platform | Advanced | 20 | 26 | 1 | 123 | 43% |
| chat-application | Advanced | 14 | 31 | 6 | 542 | 31% |
| project-management-tool | Advanced | 20 | 20 | 2 | 108 | 50% |
| social-media-platform | Intermediate | 28 | 10 | 1 | 111 | 74% |
| social-media-platform | Beginner | 21 | 7 | 3 | 140 | 75% |
| restaurant-reservation-system | Intermediate | 1 | 25 | 3 | 567 | 4% |
| chat-application | Beginner | 16 | 5 | 15 | 555 | 76% |
| chat-application | Beginner | 13 | 0 | 2 | 152 | 100% |
| chat-application | Advanced | 5 | 6 | 3 | 138 | 45% |
| restaurant-reservation-system | Beginner | 0 | 11 | 2 | 139 | 0% |
| chat-application | Intermediate | 10 | 0 | 3 | 579 | 100% |
| restaurant-reservation-system | Beginner | 0 | 10 | 4 | 580 | 0% |
| restaurant-reservation-system | Advanced | 4 | 4 | 20 | 564 | 50% |
| restaurant-reservation-system | Intermediate | 2 | 2 | 2 | 165 | 50% |
| chat-application | Intermediate | 3 | 0 | 0 | 167 | 100% |
| restaurant-reservation-system | Advanced | 0 | 2 | 4 | 144 | 0% |