| Metric | Value |
|---|---|
| Novu wins | 440 |
| SendGrid wins | 454 |
| Abstains (no tool) | 101 |
| Other tool chosen | 5395 |
| Decisive cases | 894 |
| Novu win rate (unweighted) | 49.2% |
| 95% CI | 46.0% - 52.5% |
| Novu win rate (weighted) | 49.2% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Novu | SendGrid | None | Other | A rate |
|---|---|---|---|---|---|---|
| GLM 5 Turbo | Frontier | 111 | 0 | 15 | 138 | 100% |
| Llama 4 Scout | Small | 0 | 86 | 3 | 242 | 0% |
| GPT 5.4 Mini | Mid | 1 | 79 | 8 | 246 | 1% |
| Kimi K2.5 | Frontier | 76 | 0 | 7 | 179 | 100% |
| Claude Haiku 4.5 | Small | 0 | 71 | 0 | 252 | 0% |
| Gemini 2.5 Pro | Frontier | 55 | 5 | 2 | 270 | 92% |
| GPT 5.3 Codex | Frontier | 53 | 2 | 0 | 281 | 96% |
| GPT 5.4 | Frontier | 23 | 21 | 0 | 220 | 52% |
| Claude Opus 4.6 | Frontier | 39 | 0 | 0 | 225 | 100% |
| Gemini 2.5 Flash | Small | 2 | 36 | 8 | 217 | 5% |
| Devstral 2 2512 | Mid | 0 | 36 | 0 | 285 | 0% |
| DeepSeek R1 0528 | Frontier | 0 | 31 | 24 | 279 | 0% |
| Qwen3 Coder Next | Mid | 0 | 28 | 0 | 307 | 0% |
| DeepSeek V3.2 | Mid | 11 | 13 | 12 | 226 | 46% |
| GLM 5.2 | Frontier | 21 | 0 | 0 | 51 | 100% |
| Mistral Small 4 | Mid | 0 | 20 | 1 | 307 | 0% |
| DeepSeek V4 Pro | Frontier | 11 | 0 | 0 | 61 | 100% |
| MiMo V2 Pro | Frontier | 2 | 9 | 4 | 249 | 18% |
| Gemini 3.5 Flash | Small | 10 | 0 | 0 | 62 | 100% |
| Kimi K2.7 Code | Frontier | 10 | 0 | 0 | 62 | 100% |
| DeepSeek V4 Flash | Mid | 3 | 6 | 0 | 61 | 33% |
| MiMo V2.5 Pro | Frontier | 2 | 5 | 2 | 62 | 29% |
| Claude Sonnet 4.6 | Frontier | 5 | 0 | 0 | 331 | 100% |
| MiniMax M2.7 | Frontier | 1 | 4 | 14 | 239 | 20% |
| Llama 4 Maverick | Frontier | 2 | 2 | 1 | 330 | 50% |
| MiniMax M3 | Frontier | 2 | 0 | 0 | 70 | 100% |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 71 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 0 | 72 | n/a |
| Prompt | Tier | Novu | SendGrid | None | Other | A rate |
|---|---|---|---|---|---|---|
| project-management-tool | Beginner | 110 | 103 | 22 | 299 | 52% |
| project-management-tool | Intermediate | 126 | 50 | 13 | 335 | 72% |
| project-management-tool | Advanced | 45 | 78 | 4 | 394 | 37% |
| social-media-platform | Intermediate | 48 | 56 | 1 | 429 | 46% |
| social-media-platform | Advanced | 35 | 62 | 5 | 432 | 36% |
| social-media-platform | Beginner | 39 | 33 | 6 | 459 | 54% |
| chat-application | Advanced | 10 | 30 | 6 | 488 | 25% |
| restaurant-reservation-system | Intermediate | 1 | 24 | 3 | 509 | 4% |
| chat-application | Beginner | 14 | 5 | 14 | 499 | 74% |
| restaurant-reservation-system | Beginner | 0 | 9 | 4 | 522 | 0% |
| chat-application | Intermediate | 8 | 0 | 3 | 524 | 100% |
| restaurant-reservation-system | Advanced | 4 | 4 | 20 | 505 | 50% |