| Metric | Value |
|---|---|
| Knock wins | 186 |
| Novu wins | 322 |
| Abstains (no tool) | 86 |
| Other tool chosen | 3928 |
| Decisive cases | 508 |
| Knock win rate (unweighted) | 36.6% |
| 95% CI | 32.5% - 40.9% |
| Knock win rate (weighted) | 36.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Knock | Novu | None | Other | A rate |
|---|---|---|---|---|---|---|
| Kimi K2.5 | Frontier | 55 | 69 | 7 | 107 | 44% |
| GLM 5 Turbo | Frontier | 8 | 100 | 13 | 119 | 7% |
| Gemini 2.5 Pro | Frontier | 51 | 40 | 2 | 143 | 56% |
| Claude Sonnet 4.6 | Frontier | 56 | 3 | 0 | 181 | 95% |
| GPT 5.3 Codex | Frontier | 15 | 37 | 0 | 188 | 29% |
| Claude Opus 4.6 | Frontier | 1 | 35 | 0 | 204 | 3% |
| GPT 5.4 | Frontier | 0 | 21 | 0 | 219 | 0% |
| DeepSeek V3.2 | Mid | 0 | 10 | 12 | 216 | 0% |
| Gemini 2.5 Flash | Small | 0 | 2 | 6 | 231 | 0% |
| Llama 4 Maverick | Frontier | 0 | 2 | 1 | 237 | 0% |
| MiMo V2 Pro | Frontier | 0 | 2 | 4 | 234 | 0% |
| MiniMax M2.7 | Frontier | 0 | 1 | 13 | 220 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 0 | 232 | n/a |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 19 | 219 | n/a |
| Devstral 2 2512 | Mid | 0 | 0 | 0 | 237 | n/a |
| GPT 5.4 Mini | Mid | 0 | 0 | 6 | 232 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 3 | 233 | n/a |
| Mistral Small 4 | Mid | 0 | 0 | 0 | 236 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 0 | 240 | n/a |
| Prompt | Tier | Knock | Novu | None | Other | A rate |
|---|---|---|---|---|---|---|
| project-management-tool | Intermediate | 26 | 94 | 12 | 239 | 22% |
| project-management-tool | Beginner | 9 | 78 | 19 | 273 | 10% |
| social-media-platform | Advanced | 55 | 28 | 3 | 291 | 66% |
| social-media-platform | Intermediate | 21 | 36 | 0 | 321 | 37% |
| social-media-platform | Beginner | 13 | 34 | 6 | 327 | 28% |
| project-management-tool | Advanced | 20 | 24 | 4 | 323 | 45% |
| chat-application | Advanced | 14 | 7 | 6 | 351 | 67% |
| restaurant-reservation-system | Advanced | 17 | 3 | 16 | 340 | 85% |
| chat-application | Beginner | 5 | 11 | 12 | 347 | 31% |
| chat-application | Intermediate | 2 | 7 | 3 | 367 | 22% |
| restaurant-reservation-system | Intermediate | 4 | 0 | 2 | 374 | 100% |
| restaurant-reservation-system | Beginner | 0 | 0 | 3 | 375 | n/a |