| Metric | Value |
|---|---|
| Novu wins | 436 |
| SendGrid wins | 449 |
| Abstains (no tool) | 94 |
| Other tool chosen | 5408 |
| Decisive cases | 885 |
| Novu win rate (unweighted) | 49.3% |
| 95% CI | 46.0% - 52.6% |
| Novu win rate (weighted) | 49.3% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Novu | SendGrid | None | Other | A rate |
|---|---|---|---|---|---|---|
| GLM 5 Turbo | Frontier | 107 | 0 | 14 | 131 | 100% |
| Llama 4 Scout | Small | 0 | 84 | 3 | 244 | 0% |
| GPT 5.4 Mini | Mid | 1 | 78 | 8 | 246 | 1% |
| Claude Haiku 4.5 | Small | 0 | 73 | 0 | 250 | 0% |
| Kimi K2.5 | Frontier | 71 | 0 | 5 | 174 | 100% |
| Gemini 2.5 Pro | Frontier | 54 | 6 | 2 | 270 | 90% |
| GPT 5.3 Codex | Frontier | 51 | 2 | 0 | 282 | 96% |
| GPT 5.4 | Frontier | 22 | 20 | 0 | 210 | 52% |
| Claude Opus 4.6 | Frontier | 37 | 0 | 0 | 215 | 100% |
| Gemini 2.5 Flash | Small | 2 | 34 | 8 | 207 | 6% |
| Devstral 2 2512 | Mid | 0 | 35 | 0 | 275 | 0% |
| DeepSeek R1 0528 | Frontier | 0 | 32 | 22 | 280 | 0% |
| Qwen3 Coder Next | Mid | 0 | 27 | 0 | 308 | 0% |
| GLM 5.2 | Frontier | 26 | 0 | 0 | 58 | 100% |
| DeepSeek V3.2 | Mid | 10 | 12 | 12 | 216 | 45% |
| Mistral Small 4 | Mid | 0 | 20 | 1 | 306 | 0% |
| DeepSeek V4 Pro | Frontier | 12 | 0 | 0 | 72 | 100% |
| Gemini 3.5 Flash | Small | 12 | 0 | 0 | 72 | 100% |
| Kimi K2.7 Code | Frontier | 12 | 0 | 0 | 72 | 100% |
| MiMo V2 Pro | Frontier | 2 | 8 | 4 | 238 | 20% |
| DeepSeek V4 Flash | Mid | 3 | 6 | 0 | 73 | 33% |
| MiMo V2.5 Pro | Frontier | 3 | 6 | 2 | 72 | 33% |
| Claude Sonnet 4.6 | Frontier | 5 | 0 | 0 | 331 | 100% |
| MiniMax M2.7 | Frontier | 1 | 4 | 12 | 229 | 20% |
| Llama 4 Maverick | Frontier | 2 | 2 | 1 | 330 | 50% |
| MiniMax M3 | Frontier | 3 | 0 | 0 | 81 | 100% |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 82 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 0 | 84 | n/a |
| Prompt | Tier | Novu | SendGrid | None | Other | A rate |
|---|---|---|---|---|---|---|
| project-management-tool | Beginner | 107 | 102 | 21 | 304 | 51% |
| project-management-tool | Intermediate | 126 | 51 | 12 | 334 | 71% |
| project-management-tool | Advanced | 46 | 79 | 4 | 390 | 37% |
| social-media-platform | Intermediate | 49 | 56 | 1 | 428 | 47% |
| social-media-platform | Advanced | 35 | 59 | 4 | 436 | 37% |
| social-media-platform | Beginner | 37 | 33 | 6 | 461 | 53% |
| chat-application | Advanced | 11 | 29 | 6 | 488 | 28% |
| restaurant-reservation-system | Intermediate | 1 | 24 | 2 | 510 | 4% |
| chat-application | Beginner | 13 | 5 | 13 | 501 | 72% |
| chat-application | Intermediate | 8 | 0 | 3 | 523 | 100% |
| restaurant-reservation-system | Beginner | 0 | 8 | 3 | 524 | 0% |
| restaurant-reservation-system | Advanced | 3 | 3 | 19 | 509 | 50% |