| Metric | Value |
|---|---|
| ClickHouse wins | 309 |
| Metabase wins | 412 |
| Abstains (no tool) | 344 |
| Other tool chosen | 4566 |
| Decisive cases | 721 |
| ClickHouse win rate (unweighted) | 42.9% |
| 95% CI | 39.3% - 46.5% |
| ClickHouse win rate (weighted) | 42.9% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | ClickHouse | Metabase | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Sonnet 4.6 | Frontier | 27 | 58 | 1 | 214 | 32% |
| GPT 5.3 Codex | Frontier | 46 | 30 | 1 | 222 | 61% |
| Qwen3 Coder Next | Mid | 8 | 65 | 5 | 222 | 11% |
| Kimi K2.5 | Frontier | 41 | 24 | 20 | 197 | 63% |
| Claude Opus 4.6 | Frontier | 18 | 47 | 1 | 234 | 28% |
| MiMo V2 Pro | Frontier | 10 | 50 | 22 | 218 | 17% |
| MiniMax M2.7 | Frontier | 24 | 32 | 31 | 202 | 43% |
| GPT 5.4 | Frontier | 38 | 14 | 0 | 245 | 73% |
| GLM 5 Turbo | Frontier | 23 | 26 | 59 | 192 | 47% |
| GPT 5.4 Mini | Mid | 19 | 23 | 5 | 253 | 45% |
| Claude Haiku 4.5 | Small | 19 | 12 | 4 | 256 | 61% |
| Mistral Small 4 | Mid | 11 | 12 | 2 | 261 | 48% |
| Gemini 2.5 Flash | Small | 14 | 0 | 21 | 262 | 100% |
| Gemini 2.5 Pro | Frontier | 4 | 6 | 22 | 266 | 40% |
| DeepSeek R1 0528 | Frontier | 0 | 10 | 106 | 182 | 0% |
| DeepSeek V3.2 | Mid | 5 | 3 | 25 | 265 | 63% |
| Llama 4 Maverick | Frontier | 2 | 0 | 0 | 297 | 100% |
| Devstral 2 2512 | Mid | 0 | 0 | 0 | 298 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 19 | 280 | n/a |
| Prompt | Tier | ClickHouse | Metabase | None | Other | A rate |
|---|---|---|---|---|---|---|
| url-shortener | Advanced | 197 | 0 | 4 | 175 | 100% |
| ai-revenue-ops-copilot | Beginner | 0 | 172 | 5 | 189 | 0% |
| multi-tenant-crm | Advanced | 41 | 64 | 28 | 247 | 39% |
| multi-tenant-crm | Intermediate | 0 | 91 | 27 | 255 | 0% |
| ai-revenue-ops-copilot | Advanced | 2 | 55 | 14 | 288 | 4% |
| url-shortener | Intermediate | 37 | 0 | 51 | 290 | 100% |
| fitness-tracking-app | Advanced | 32 | 5 | 8 | 328 | 86% |
| multi-tenant-crm | Beginner | 0 | 16 | 33 | 329 | 0% |
| ai-revenue-ops-copilot | Intermediate | 0 | 9 | 3 | 361 | 0% |
| fitness-tracking-app | Beginner | 0 | 0 | 1 | 378 | n/a |
| fitness-tracking-app | Intermediate | 0 | 0 | 10 | 370 | n/a |
| saas-application | Beginner | 0 | 0 | 13 | 367 | n/a |
| saas-application | Intermediate | 0 | 0 | 44 | 334 | n/a |
| saas-application | Advanced | 0 | 0 | 24 | 355 | n/a |
| url-shortener | Beginner | 0 | 0 | 79 | 300 | n/a |