| Metric | Value |
|---|---|
| Knock wins | 372 |
| Novu wins | 436 |
| Abstains (no tool) | 94 |
| Other tool chosen | 5485 |
| Decisive cases | 808 |
| Knock win rate (unweighted) | 46.0% |
| 95% CI | 42.6% - 49.5% |
| Knock win rate (weighted) | 46.0% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Knock | Novu | None | Other | A rate |
|---|---|---|---|---|---|---|
| Kimi K2.5 | Frontier | 60 | 71 | 5 | 114 | 46% |
| Gemini 2.5 Pro | Frontier | 69 | 54 | 2 | 207 | 56% |
| GLM 5 Turbo | Frontier | 8 | 107 | 14 | 123 | 7% |
| Claude Sonnet 4.6 | Frontier | 85 | 5 | 0 | 246 | 94% |
| GPT 5.3 Codex | Frontier | 20 | 51 | 0 | 264 | 28% |
| MiniMax M3 | Frontier | 36 | 3 | 0 | 45 | 92% |
| Claude Opus 4.6 | Frontier | 1 | 37 | 0 | 214 | 3% |
| Kimi K2.7 Code | Frontier | 22 | 12 | 0 | 50 | 65% |
| Gemini 3.5 Flash | Small | 16 | 12 | 0 | 56 | 57% |
| GLM 5.2 | Frontier | 2 | 26 | 0 | 56 | 7% |
| GPT 5.5 | Frontier | 26 | 0 | 0 | 58 | 100% |
| Claude Opus 4.8 | Frontier | 22 | 0 | 0 | 60 | 100% |
| GPT 5.4 | Frontier | 0 | 22 | 0 | 230 | 0% |
| DeepSeek V4 Pro | Frontier | 1 | 12 | 0 | 71 | 8% |
| DeepSeek V3.2 | Mid | 0 | 10 | 12 | 228 | 0% |
| DeepSeek V4 Flash | Mid | 3 | 3 | 0 | 76 | 50% |
| MiMo V2.5 Pro | Frontier | 0 | 3 | 2 | 78 | 0% |
| MiniMax M2.7 | Frontier | 1 | 1 | 12 | 232 | 50% |
| Gemini 2.5 Flash | Small | 0 | 2 | 8 | 241 | 0% |
| Llama 4 Maverick | Frontier | 0 | 2 | 1 | 332 | 0% |
| MiMo V2 Pro | Frontier | 0 | 2 | 4 | 246 | 0% |
| GPT 5.4 Mini | Mid | 0 | 1 | 8 | 324 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 0 | 323 | n/a |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 22 | 312 | n/a |
| Devstral 2 2512 | Mid | 0 | 0 | 0 | 310 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 3 | 328 | n/a |
| Mistral Small 4 | Mid | 0 | 0 | 1 | 326 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 0 | 335 | n/a |
| Prompt | Tier | Knock | Novu | None | Other | A rate |
|---|---|---|---|---|---|---|
| project-management-tool | Intermediate | 66 | 126 | 12 | 319 | 34% |
| project-management-tool | Beginner | 24 | 107 | 21 | 382 | 18% |
| social-media-platform | Advanced | 95 | 35 | 4 | 400 | 73% |
| project-management-tool | Advanced | 57 | 46 | 4 | 412 | 55% |
| social-media-platform | Intermediate | 42 | 49 | 1 | 442 | 46% |
| social-media-platform | Beginner | 23 | 37 | 6 | 471 | 38% |
| chat-application | Advanced | 19 | 11 | 6 | 498 | 63% |
| restaurant-reservation-system | Advanced | 25 | 3 | 19 | 487 | 89% |
| chat-application | Beginner | 7 | 13 | 13 | 499 | 35% |
| chat-application | Intermediate | 6 | 8 | 3 | 517 | 43% |
| restaurant-reservation-system | Intermediate | 8 | 1 | 2 | 526 | 89% |
| restaurant-reservation-system | Beginner | 0 | 0 | 3 | 532 | n/a |