| Metric | Value |
|---|---|
| Knock wins | 465 |
| Novu wins | 658 |
| Abstains (no tool) | 146 |
| Other tool chosen | 7731 |
| Decisive cases | 1123 |
| Knock win rate (unweighted) | 41.4% |
| 95% CI | 38.6% - 44.3% |
| Knock win rate (weighted) | 41.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Knock | Novu | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 7 | 25 | 20 | 417 | 22% |
| DeepSeek Pro 4–4 0813 | Frontier | 1 | 14 | 0 | 93 | 7% |
| DeepSeek R1 | Frontier | 0 | 1 | 34 | 435 | 0% |
| Devstral | Mid | 0 | 0 | 0 | 446 | n/a |
| Gemini Flash 2.5–3.8 | Small | 28 | 15 | 12 | 416 | 65% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 89 | 89 | 2 | 288 | 50% |
| GLM 5 Turbo–5.3 | Frontier | 13 | 188 | 18 | 253 | 6% |
| GPT 5.4–6 Astra | Frontier | 32 | 33 | 1 | 406 | 49% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 29 | 78 | 1 | 364 | 27% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 0 | 5 | 16 | 449 | 0% |
| Haiku | Small | 0 | 0 | 1 | 458 | n/a |
| Kimi 2.5–3 | Frontier | 96 | 128 | 8 | 238 | 43% |
| Llama Maverick | Frontier | 0 | 2 | 1 | 469 | 0% |
| Llama Scout | Small | 0 | 0 | 4 | 463 | n/a |
| MiMo Pro 2–2.6 | Frontier | 1 | 19 | 7 | 444 | 5% |
| MiniMax M 2.7–3 | Frontier | 43 | 7 | 19 | 397 | 86% |
| Mistral Small | Mid | 0 | 0 | 1 | 460 | n/a |
| Opus 4.6–5.5 | Frontier | 29 | 42 | 0 | 400 | 41% |
| Qwen Coder | Mid | 0 | 0 | 1 | 471 | n/a |
| Sonnet 4.6–5.5 | Frontier | 97 | 12 | 0 | 364 | 89% |
| Prompt | Tier | Knock | Novu | None | Other | A rate |
|---|---|---|---|---|---|---|
| project-management-tool | Intermediate | 79 | 140 | 16 | 346 | 36% |
| social-media-platform | Advanced | 108 | 40 | 6 | 440 | 73% |
| project-management-tool | Beginner | 31 | 114 | 23 | 425 | 21% |
| project-management-tool | Advanced | 73 | 49 | 5 | 452 | 60% |
| social-media-platform | Intermediate | 52 | 57 | 1 | 483 | 48% |
| social-media-platform | Beginner | 27 | 42 | 7 | 520 | 39% |
| project-management-tool | Intermediate | 0 | 37 | 6 | 109 | 0% |
| chat-application | Advanced | 22 | 14 | 6 | 551 | 61% |
| social-media-platform | Advanced | 12 | 20 | 1 | 137 | 38% |
| social-media-platform | Intermediate | 4 | 28 | 1 | 117 | 13% |
| restaurant-reservation-system | Advanced | 26 | 4 | 20 | 542 | 87% |
| chat-application | Beginner | 8 | 16 | 15 | 552 | 33% |
| project-management-tool | Advanced | 3 | 20 | 2 | 125 | 13% |
| social-media-platform | Beginner | 1 | 21 | 3 | 146 | 5% |
| project-management-tool | Beginner | 0 | 22 | 11 | 118 | 0% |
| chat-application | Intermediate | 6 | 10 | 3 | 573 | 38% |
| chat-application | Beginner | 1 | 13 | 2 | 151 | 7% |
| restaurant-reservation-system | Intermediate | 8 | 1 | 3 | 584 | 89% |
| chat-application | Advanced | 2 | 5 | 3 | 142 | 29% |
| chat-application | Intermediate | 1 | 3 | 0 | 166 | 25% |
| restaurant-reservation-system | Intermediate | 0 | 2 | 2 | 167 | 0% |
| restaurant-reservation-system | Advanced | 1 | 0 | 4 | 145 | 100% |
| restaurant-reservation-system | Beginner | 0 | 0 | 4 | 590 | n/a |
| restaurant-reservation-system | Beginner | 0 | 0 | 2 | 150 | n/a |