| Metric | Value |
|---|---|
| PostHog wins | 3303 |
| Mixpanel wins | 1823 |
| Abstains (no tool) | 725 |
| Other tool chosen | 4638 |
| Decisive cases | 5126 |
| PostHog win rate (unweighted) | 64.4% |
| 95% CI | 63.1% - 65.7% |
| PostHog win rate (weighted) | 64.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | PostHog | Mixpanel | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 176 | 131 | 47 | 194 | 57% |
| DeepSeek Pro 4–4 0813 | Frontier | 46 | 2 | 19 | 52 | 96% |
| DeepSeek R1 | Frontier | 23 | 110 | 200 | 217 | 17% |
| Devstral | Mid | 15 | 225 | 6 | 273 | 6% |
| Gemini Flash 2.5–3.8 | Small | 102 | 208 | 34 | 206 | 33% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 264 | 17 | 48 | 218 | 94% |
| GLM 5 Turbo–5.3 | Frontier | 317 | 4 | 91 | 141 | 99% |
| GPT 5.4–6 Astra | Frontier | 307 | 22 | 8 | 208 | 93% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 250 | 26 | 16 | 260 | 91% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 330 | 17 | 10 | 193 | 95% |
| Haiku | Small | 123 | 162 | 24 | 230 | 43% |
| Kimi 2.5–3 | Frontier | 257 | 8 | 40 | 228 | 97% |
| Llama Maverick | Frontier | 7 | 353 | 0 | 192 | 2% |
| Llama Scout | Small | 0 | 73 | 28 | 450 | 0% |
| MiMo Pro 2–2.6 | Frontier | 38 | 134 | 54 | 324 | 22% |
| MiniMax M 2.7–3 | Frontier | 243 | 36 | 67 | 196 | 87% |
| Mistral Small | Mid | 189 | 67 | 3 | 274 | 74% |
| Opus 4.6–5.5 | Frontier | 213 | 65 | 16 | 258 | 77% |
| Qwen Coder | Mid | 237 | 52 | 8 | 254 | 82% |
| Sonnet 4.6–5.5 | Frontier | 166 | 111 | 6 | 270 | 60% |
| Prompt | Tier | PostHog | Mixpanel | None | Other | A rate |
|---|---|---|---|---|---|---|
| saas-application | Beginner | 397 | 145 | 18 | 16 | 73% |
| saas-application | Intermediate | 385 | 109 | 55 | 25 | 78% |
| fitness-tracking-app | Intermediate | 235 | 230 | 18 | 93 | 51% |
| ai-revenue-ops-copilot | Intermediate | 293 | 167 | 3 | 105 | 64% |
| multi-tenant-crm | Beginner | 263 | 158 | 53 | 98 | 62% |
| multi-tenant-crm | Intermediate | 203 | 133 | 36 | 197 | 60% |
| saas-application | Advanced | 207 | 85 | 32 | 251 | 71% |
| fitness-tracking-app | Beginner | 143 | 142 | 1 | 289 | 50% |
| url-shortener | Intermediate | 193 | 65 | 81 | 235 | 75% |
| url-shortener | Beginner | 136 | 46 | 123 | 269 | 75% |
| ai-revenue-ops-copilot | Advanced | 59 | 89 | 16 | 381 | 40% |
| saas-application | Intermediate | 128 | 16 | 7 | 20 | 89% |
| saas-application | Beginner | 109 | 33 | 6 | 21 | 77% |
| fitness-tracking-app | Advanced | 29 | 83 | 14 | 436 | 26% |
| ai-revenue-ops-copilot | Beginner | 39 | 66 | 5 | 448 | 37% |
| fitness-tracking-app | Intermediate | 64 | 35 | 20 | 33 | 65% |
| multi-tenant-crm | Beginner | 70 | 20 | 31 | 47 | 78% |
| saas-application | Advanced | 65 | 25 | 9 | 71 | 72% |
| fitness-tracking-app | Beginner | 52 | 38 | 2 | 78 | 58% |
| url-shortener | Advanced | 35 | 43 | 5 | 488 | 45% |
| multi-tenant-crm | Advanced | 46 | 26 | 38 | 465 | 64% |
| multi-tenant-crm | Intermediate | 52 | 13 | 25 | 62 | 80% |
| url-shortener | Intermediate | 41 | 9 | 49 | 52 | 82% |
| multi-tenant-crm | Advanced | 22 | 22 | 8 | 118 | 50% |
| fitness-tracking-app | Advanced | 13 | 21 | 3 | 132 | 38% |
| url-shortener | Beginner | 22 | 0 | 62 | 68 | 100% |
| url-shortener | Advanced | 2 | 4 | 5 | 140 | 33% |