| Metric | Value |
|---|---|
| Knock wins | 355 |
| Novu wins | 440 |
| Abstains (no tool) | 101 |
| Other tool chosen | 5494 |
| Decisive cases | 795 |
| Knock win rate (unweighted) | 44.7% |
| 95% CI | 41.2% - 48.1% |
| Knock win rate (weighted) | 44.7% |
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 | 76 | 7 | 119 | 44% |
| Gemini 2.5 Pro | Frontier | 70 | 55 | 2 | 205 | 56% |
| GLM 5 Turbo | Frontier | 8 | 111 | 15 | 130 | 7% |
| Claude Sonnet 4.6 | Frontier | 83 | 5 | 0 | 248 | 94% |
| GPT 5.3 Codex | Frontier | 19 | 53 | 0 | 264 | 26% |
| Claude Opus 4.6 | Frontier | 1 | 39 | 0 | 224 | 3% |
| MiniMax M3 | Frontier | 32 | 2 | 0 | 38 | 94% |
| Kimi K2.7 Code | Frontier | 20 | 10 | 0 | 42 | 67% |
| Gemini 3.5 Flash | Small | 14 | 10 | 0 | 48 | 58% |
| GLM 5.2 | Frontier | 2 | 21 | 0 | 49 | 9% |
| GPT 5.4 | Frontier | 0 | 23 | 0 | 241 | 0% |
| GPT 5.5 | Frontier | 22 | 0 | 0 | 50 | 100% |
| Claude Opus 4.8 | Frontier | 19 | 0 | 0 | 52 | 100% |
| DeepSeek V4 Pro | Frontier | 1 | 11 | 0 | 60 | 8% |
| DeepSeek V3.2 | Mid | 0 | 11 | 12 | 239 | 0% |
| DeepSeek V4 Flash | Mid | 3 | 3 | 0 | 64 | 50% |
| MiniMax M2.7 | Frontier | 1 | 1 | 14 | 242 | 50% |
| Gemini 2.5 Flash | Small | 0 | 2 | 8 | 253 | 0% |
| Llama 4 Maverick | Frontier | 0 | 2 | 1 | 332 | 0% |
| MiMo V2 Pro | Frontier | 0 | 2 | 4 | 258 | 0% |
| MiMo V2.5 Pro | Frontier | 0 | 2 | 2 | 67 | 0% |
| GPT 5.4 Mini | Mid | 0 | 1 | 8 | 325 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 0 | 323 | n/a |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 24 | 310 | n/a |
| Devstral 2 2512 | Mid | 0 | 0 | 0 | 321 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 3 | 328 | n/a |
| Mistral Small 4 | Mid | 0 | 0 | 1 | 327 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 0 | 335 | n/a |
| Prompt | Tier | Knock | Novu | None | Other | A rate |
|---|---|---|---|---|---|---|
| project-management-tool | Intermediate | 61 | 126 | 13 | 324 | 33% |
| project-management-tool | Beginner | 23 | 110 | 22 | 379 | 17% |
| social-media-platform | Advanced | 92 | 35 | 5 | 402 | 72% |
| project-management-tool | Advanced | 52 | 45 | 4 | 420 | 54% |
| social-media-platform | Intermediate | 40 | 48 | 1 | 445 | 45% |
| social-media-platform | Beginner | 23 | 39 | 6 | 469 | 37% |
| chat-application | Advanced | 19 | 10 | 6 | 499 | 66% |
| restaurant-reservation-system | Advanced | 24 | 4 | 20 | 485 | 86% |
| chat-application | Beginner | 7 | 14 | 14 | 497 | 33% |
| chat-application | Intermediate | 6 | 8 | 3 | 518 | 43% |
| restaurant-reservation-system | Intermediate | 8 | 1 | 3 | 525 | 89% |
| restaurant-reservation-system | Beginner | 0 | 0 | 4 | 531 | n/a |