| Metric | Value |
|---|---|
| Metabase wins | 438 |
| Mixpanel wins | 1219 |
| Abstains (no tool) | 364 |
| Other tool chosen | 3893 |
| Decisive cases | 1657 |
| Metabase win rate (unweighted) | 26.4% |
| 95% CI | 24.4% - 28.6% |
| Metabase win rate (weighted) | 26.4% |
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 | 214 | 0 | 100 | 0% |
| Devstral 2 2512 | Mid | 0 | 164 | 0 | 149 | 0% |
| Gemini 2.5 Flash | Small | 0 | 163 | 21 | 128 | 0% |
| MiMo V2 Pro | Frontier | 54 | 79 | 24 | 158 | 41% |
| Claude Sonnet 4.6 | Frontier | 61 | 65 | 1 | 188 | 48% |
| Claude Haiku 4.5 | Small | 12 | 102 | 4 | 187 | 11% |
| DeepSeek V3.2 | Mid | 3 | 106 | 26 | 178 | 3% |
| Qwen3 Coder Next | Mid | 69 | 28 | 5 | 213 | 71% |
| Claude Opus 4.6 | Frontier | 50 | 46 | 1 | 218 | 52% |
| DeepSeek R1 0528 | Frontier | 10 | 73 | 114 | 116 | 12% |
| MiniMax M2.7 | Frontier | 35 | 28 | 34 | 207 | 56% |
| Mistral Small 4 | Mid | 13 | 44 | 2 | 242 | 23% |
| Llama 4 Scout | Small | 0 | 48 | 20 | 246 | 0% |
| GPT 5.3 Codex | Frontier | 32 | 15 | 1 | 266 | 68% |
| GPT 5.4 Mini | Mid | 24 | 11 | 5 | 275 | 69% |
| GPT 5.4 | Frontier | 15 | 18 | 0 | 279 | 45% |
| GLM 5 Turbo | Frontier | 27 | 4 | 61 | 223 | 87% |
| Kimi K2.5 | Frontier | 27 | 2 | 22 | 246 | 93% |
| Gemini 2.5 Pro | Frontier | 6 | 9 | 23 | 274 | 40% |
| Prompt | Tier | Metabase | Mixpanel | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Beginner | 183 | 53 | 5 | 144 | 78% |
| multi-tenant-crm | Intermediate | 97 | 106 | 28 | 161 | 48% |
| fitness-tracking-app | Intermediate | 0 | 181 | 12 | 206 | 0% |
| multi-tenant-crm | Beginner | 17 | 122 | 35 | 223 | 12% |
| ai-revenue-ops-copilot | Intermediate | 9 | 125 | 3 | 255 | 7% |
| ai-revenue-ops-copilot | Advanced | 59 | 69 | 14 | 235 | 46% |
| saas-application | Beginner | 0 | 111 | 13 | 275 | 0% |
| fitness-tracking-app | Beginner | 0 | 107 | 1 | 290 | 0% |
| multi-tenant-crm | Advanced | 68 | 20 | 31 | 279 | 77% |
| saas-application | Intermediate | 0 | 79 | 45 | 273 | 0% |
| fitness-tracking-app | Advanced | 5 | 64 | 9 | 314 | 7% |
| saas-application | Advanced | 0 | 60 | 25 | 313 | 0% |
| url-shortener | Intermediate | 0 | 52 | 55 | 290 | 0% |
| url-shortener | Beginner | 0 | 37 | 84 | 277 | 0% |
| url-shortener | Advanced | 0 | 33 | 4 | 358 | 0% |
