| Metric | Value |
|---|---|
| Mixpanel wins | 1851 |
| PostHog wins | 3432 |
| Abstains (no tool) | 748 |
| Other tool chosen | 4757 |
| Decisive cases | 5283 |
| Mixpanel win rate (unweighted) | 35.0% |
| 95% CI | 33.8% - 36.3% |
| Mixpanel win rate (weighted) | 35.0% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Mixpanel | PostHog | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 131 | 186 | 47 | 198 | 41% |
| DeepSeek Pro 4–4 0813 | Frontier | 3 | 54 | 19 | 58 | 5% |
| DeepSeek R1 | Frontier | 113 | 23 | 205 | 224 | 83% |
| Devstral | Mid | 230 | 15 | 6 | 284 | 94% |
| Gemini Flash 2.5–3.8 | Small | 208 | 112 | 35 | 210 | 65% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 18 | 271 | 48 | 225 | 6% |
| GLM 5 Turbo–5.3 | Frontier | 4 | 328 | 91 | 145 | 1% |
| GPT 5.4–6 Astra | Frontier | 22 | 311 | 12 | 214 | 7% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 26 | 257 | 18 | 266 | 9% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 17 | 339 | 11 | 198 | 5% |
| Haiku | Small | 166 | 127 | 24 | 236 | 57% |
| Kimi 2.5–3 | Frontier | 8 | 265 | 42 | 233 | 3% |
| Llama Maverick | Frontier | 361 | 7 | 0 | 199 | 98% |
| Llama Scout | Small | 76 | 0 | 29 | 461 | 100% |
| MiMo Pro 2–2.6 | Frontier | 134 | 47 | 55 | 329 | 74% |
| MiniMax M 2.7–3 | Frontier | 36 | 257 | 68 | 196 | 12% |
| Mistral Small | Mid | 69 | 194 | 3 | 283 | 26% |
| Opus 4.6–5.5 | Frontier | 65 | 223 | 17 | 262 | 23% |
| Qwen Coder | Mid | 53 | 244 | 8 | 261 | 18% |
| Sonnet 4.6–5.5 | Frontier | 111 | 172 | 10 | 275 | 39% |
| Prompt | Tier | Mixpanel | PostHog | None | Other | A rate |
|---|---|---|---|---|---|---|
| saas-application | Beginner | 147 | 413 | 18 | 18 | 26% |
| saas-application | Intermediate | 112 | 399 | 57 | 26 | 22% |
| fitness-tracking-app | Intermediate | 236 | 246 | 19 | 95 | 49% |
| ai-revenue-ops-copilot | Intermediate | 171 | 307 | 3 | 106 | 36% |
| multi-tenant-crm | Beginner | 161 | 274 | 57 | 100 | 37% |
| multi-tenant-crm | Intermediate | 136 | 213 | 37 | 203 | 39% |
| saas-application | Advanced | 87 | 219 | 33 | 256 | 28% |
| fitness-tracking-app | Beginner | 143 | 155 | 1 | 296 | 48% |
| url-shortener | Intermediate | 66 | 202 | 85 | 241 | 25% |
| url-shortener | Beginner | 46 | 142 | 132 | 274 | 24% |
| ai-revenue-ops-copilot | Advanced | 91 | 64 | 16 | 393 | 59% |
| saas-application | Intermediate | 16 | 128 | 7 | 20 | 11% |
| saas-application | Beginner | 33 | 109 | 6 | 21 | 23% |
| fitness-tracking-app | Advanced | 84 | 33 | 15 | 449 | 72% |
| ai-revenue-ops-copilot | Beginner | 66 | 41 | 5 | 468 | 62% |
| fitness-tracking-app | Intermediate | 35 | 64 | 20 | 33 | 35% |
| fitness-tracking-app | Beginner | 38 | 52 | 2 | 78 | 42% |
| saas-application | Advanced | 25 | 65 | 9 | 71 | 28% |
| multi-tenant-crm | Beginner | 20 | 70 | 31 | 47 | 22% |
| url-shortener | Advanced | 43 | 37 | 5 | 506 | 54% |
| multi-tenant-crm | Advanced | 26 | 47 | 38 | 484 | 36% |
| multi-tenant-crm | Intermediate | 13 | 52 | 25 | 62 | 20% |
| url-shortener | Intermediate | 9 | 41 | 49 | 52 | 18% |
| multi-tenant-crm | Advanced | 22 | 22 | 8 | 118 | 50% |
| fitness-tracking-app | Advanced | 21 | 13 | 3 | 132 | 62% |
| url-shortener | Beginner | 0 | 22 | 62 | 68 | 0% |
| url-shortener | Advanced | 4 | 2 | 5 | 140 | 67% |