| Metric | Value |
|---|---|
| Metabase wins | 552 |
| Mixpanel wins | 1456 |
| Abstains (no tool) | 530 |
| Other tool chosen | 5091 |
| Decisive cases | 2008 |
| Metabase win rate (unweighted) | 27.5% |
| 95% CI | 25.6% - 29.5% |
| Metabase win rate (weighted) | 27.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Metabase | Mixpanel | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 0 | 267 | 0 | 137 | 0% |
| Devstral 2 2512 | Mid | 5 | 186 | 3 | 209 | 3% |
| Gemini 2.5 Flash | Small | 0 | 188 | 30 | 169 | 0% |
| MiMo V2 Pro | Frontier | 71 | 101 | 34 | 184 | 41% |
| Claude Sonnet 4.6 | Frontier | 78 | 85 | 1 | 241 | 48% |
| Claude Haiku 4.5 | Small | 12 | 117 | 15 | 250 | 9% |
| DeepSeek V3.2 | Mid | 5 | 120 | 33 | 229 | 4% |
| Claude Opus 4.6 | Frontier | 58 | 59 | 9 | 264 | 50% |
| Qwen3 Coder Next | Mid | 81 | 34 | 8 | 282 | 70% |
| DeepSeek R1 0528 | Frontier | 17 | 90 | 148 | 148 | 16% |
| Mistral Small 4 | Mid | 19 | 51 | 2 | 317 | 27% |
| MiniMax M2.7 | Frontier | 38 | 31 | 52 | 258 | 55% |
| GPT 5.3 Codex | Frontier | 40 | 17 | 10 | 337 | 70% |
| Llama 4 Scout | Small | 0 | 54 | 21 | 329 | 0% |
| GPT 5.4 Mini | Mid | 26 | 14 | 5 | 360 | 65% |
| GPT 5.4 | Frontier | 18 | 20 | 2 | 347 | 47% |
| Kimi K2.5 | Frontier | 32 | 3 | 33 | 302 | 91% |
| GLM 5 Turbo | Frontier | 29 | 4 | 81 | 276 | 88% |
| Gemini 2.5 Pro | Frontier | 8 | 11 | 36 | 345 | 42% |
| MiMo V2.5 Pro | Frontier | 4 | 1 | 2 | 8 | 80% |
| Kimi K2.7 Code | Frontier | 3 | 1 | 0 | 11 | 75% |
| DeepSeek V4 Flash | Mid | 2 | 2 | 2 | 9 | 50% |
| DeepSeek V4 Pro | Frontier | 3 | 0 | 3 | 8 | 100% |
| GPT 5.5 | Frontier | 2 | 0 | 0 | 12 | 100% |
| GLM 5.2 | Frontier | 1 | 0 | 0 | 14 | 100% |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 15 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 0 | 15 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 0 | 15 | n/a |
| Prompt | Tier | Metabase | Mixpanel | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Beginner | 204 | 56 | 5 | 157 | 78% |
| multi-tenant-crm | Intermediate | 107 | 114 | 29 | 181 | 48% |
| fitness-tracking-app | Intermediate | 0 | 195 | 14 | 229 | 0% |
| multi-tenant-crm | Beginner | 20 | 130 | 38 | 247 | 13% |
| ai-revenue-ops-copilot | Intermediate | 9 | 136 | 3 | 283 | 6% |
| ai-revenue-ops-copilot | Advanced | 67 | 75 | 14 | 257 | 47% |
| saas-application | Beginner | 0 | 121 | 14 | 303 | 0% |
| fitness-tracking-app | Beginner | 0 | 113 | 1 | 323 | 0% |
| multi-tenant-crm | Advanced | 77 | 22 | 33 | 305 | 78% |
| saas-application | Intermediate | 0 | 88 | 47 | 301 | 0% |
| fitness-tracking-app | Advanced | 5 | 66 | 11 | 348 | 7% |
| saas-application | Advanced | 0 | 65 | 26 | 346 | 0% |
| url-shortener | Intermediate | 0 | 57 | 62 | 317 | 0% |
| url-shortener | Beginner | 0 | 41 | 91 | 305 | 0% |
| multi-tenant-crm | Intermediate | 31 | 8 | 19 | 37 | 79% |
| multi-tenant-crm | Advanced | 24 | 13 | 5 | 53 | 65% |
| url-shortener | Advanced | 0 | 36 | 4 | 394 | 0% |
| fitness-tracking-app | Intermediate | 0 | 24 | 10 | 61 | 0% |
| fitness-tracking-app | Beginner | 0 | 21 | 1 | 73 | 0% |
| saas-application | Beginner | 0 | 20 | 4 | 71 | 0% |
| multi-tenant-crm | Beginner | 4 | 11 | 16 | 64 | 27% |
| saas-application | Advanced | 0 | 15 | 6 | 74 | 0% |
| fitness-tracking-app | Advanced | 1 | 13 | 3 | 76 | 7% |
| url-shortener | Intermediate | 3 | 7 | 26 | 58 | 30% |
| saas-application | Intermediate | 0 | 7 | 4 | 84 | 0% |
| url-shortener | Advanced | 0 | 2 | 4 | 89 | 0% |
| url-shortener | Beginner | 0 | 0 | 40 | 55 | n/a |