| Metric | Value |
|---|---|
| Metabase wins | 777 |
| Mixpanel wins | 1851 |
| Abstains (no tool) | 748 |
| Other tool chosen | 7412 |
| Decisive cases | 2628 |
| Metabase win rate (unweighted) | 29.6% |
| 95% CI | 27.9% - 31.3% |
| Metabase win rate (weighted) | 29.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Metabase | Mixpanel | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 30 | 131 | 47 | 354 | 19% |
| DeepSeek Pro 4–4 0813 | Frontier | 18 | 3 | 19 | 94 | 86% |
| DeepSeek R1 | Frontier | 28 | 113 | 205 | 219 | 20% |
| Devstral | Mid | 7 | 230 | 6 | 292 | 3% |
| Gemini Flash 2.5–3.8 | Small | 4 | 208 | 35 | 318 | 2% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 13 | 18 | 48 | 483 | 42% |
| GLM 5 Turbo–5.3 | Frontier | 40 | 4 | 91 | 433 | 91% |
| GPT 5.4–6 Astra | Frontier | 37 | 22 | 12 | 488 | 63% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 55 | 26 | 18 | 468 | 68% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 34 | 17 | 11 | 503 | 67% |
| Haiku | Small | 12 | 166 | 24 | 351 | 7% |
| Kimi 2.5–3 | Frontier | 53 | 8 | 42 | 445 | 87% |
| Llama Maverick | Frontier | 0 | 361 | 0 | 206 | 0% |
| Llama Scout | Small | 0 | 76 | 29 | 461 | 0% |
| MiMo Pro 2–2.6 | Frontier | 102 | 134 | 55 | 274 | 43% |
| MiniMax M 2.7–3 | Frontier | 41 | 36 | 68 | 412 | 53% |
| Mistral Small | Mid | 27 | 69 | 3 | 450 | 28% |
| Opus 4.6–5.5 | Frontier | 68 | 65 | 17 | 417 | 51% |
| Qwen Coder | Mid | 104 | 53 | 8 | 401 | 66% |
| Sonnet 4.6–5.5 | Frontier | 104 | 111 | 10 | 343 | 48% |
| Prompt | Tier | Metabase | Mixpanel | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Beginner | 294 | 66 | 5 | 215 | 82% |
| multi-tenant-crm | Intermediate | 155 | 136 | 37 | 261 | 53% |
| fitness-tracking-app | Intermediate | 1 | 236 | 19 | 340 | 0% |
| multi-tenant-crm | Beginner | 23 | 161 | 57 | 351 | 13% |
| ai-revenue-ops-copilot | Intermediate | 10 | 171 | 3 | 403 | 6% |
| ai-revenue-ops-copilot | Advanced | 85 | 91 | 16 | 372 | 48% |
| saas-application | Beginner | 0 | 147 | 18 | 431 | 0% |
| fitness-tracking-app | Beginner | 0 | 143 | 1 | 451 | 0% |
| multi-tenant-crm | Advanced | 98 | 26 | 38 | 433 | 79% |
| saas-application | Intermediate | 0 | 112 | 57 | 425 | 0% |
| fitness-tracking-app | Advanced | 5 | 84 | 15 | 477 | 6% |
| saas-application | Advanced | 1 | 87 | 33 | 474 | 1% |
| url-shortener | Intermediate | 0 | 66 | 85 | 443 | 0% |
| multi-tenant-crm | Intermediate | 52 | 13 | 25 | 62 | 80% |
| multi-tenant-crm | Advanced | 43 | 22 | 8 | 97 | 66% |
| url-shortener | Beginner | 0 | 46 | 132 | 416 | 0% |
| url-shortener | Advanced | 0 | 43 | 5 | 543 | 0% |
| fitness-tracking-app | Beginner | 0 | 38 | 2 | 130 | 0% |
| fitness-tracking-app | Intermediate | 0 | 35 | 20 | 97 | 0% |
| saas-application | Beginner | 0 | 33 | 6 | 130 | 0% |
| multi-tenant-crm | Beginner | 6 | 20 | 31 | 111 | 23% |
| saas-application | Advanced | 0 | 25 | 9 | 136 | 0% |
| fitness-tracking-app | Advanced | 1 | 21 | 3 | 144 | 5% |
| saas-application | Intermediate | 0 | 16 | 7 | 148 | 0% |
| url-shortener | Intermediate | 3 | 9 | 49 | 90 | 25% |
| url-shortener | Advanced | 0 | 4 | 5 | 142 | 0% |
| url-shortener | Beginner | 0 | 0 | 62 | 90 | n/a |