| Metric | Value |
|---|---|
| PostHog wins | 2459 |
| Mixpanel wins | 1499 |
| Abstains (no tool) | 460 |
| Other tool chosen | 3549 |
| Decisive cases | 3958 |
| PostHog win rate (unweighted) | 62.1% |
| 95% CI | 60.6% - 63.6% |
| PostHog win rate (weighted) | 62.1% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | PostHog | Mixpanel | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 1 | 282 | 0 | 136 | 0% |
| GPT 5.4 Mini | Mid | 249 | 16 | 7 | 147 | 94% |
| Claude Haiku 4.5 | Small | 76 | 146 | 6 | 179 | 34% |
| Qwen3 Coder Next | Mid | 177 | 40 | 5 | 197 | 82% |
| Gemini 2.5 Pro | Frontier | 202 | 14 | 23 | 177 | 94% |
| Claude Sonnet 4.6 | Frontier | 127 | 86 | 1 | 206 | 60% |
| GPT 5.3 Codex | Frontier | 183 | 25 | 1 | 210 | 88% |
| Devstral 2 2512 | Mid | 6 | 191 | 0 | 191 | 3% |
| Mistral Small 4 | Mid | 139 | 55 | 3 | 205 | 72% |
| GPT 5.4 | Frontier | 170 | 19 | 0 | 123 | 90% |
| DeepSeek V3.2 | Mid | 84 | 104 | 26 | 98 | 45% |
| GLM 5 Turbo | Frontier | 172 | 3 | 63 | 77 | 98% |
| Gemini 2.5 Flash | Small | 5 | 161 | 21 | 125 | 3% |
| Claude Opus 4.6 | Frontier | 106 | 46 | 1 | 162 | 70% |
| Kimi K2.5 | Frontier | 145 | 3 | 23 | 129 | 98% |
| MiniMax M2.7 | Frontier | 101 | 26 | 36 | 141 | 80% |
| DeepSeek R1 0528 | Frontier | 15 | 90 | 150 | 163 | 14% |
| MiniMax M3 | Frontier | 93 | 1 | 3 | 8 | 99% |
| MiMo V2 Pro | Frontier | 10 | 81 | 24 | 200 | 11% |
| Gemini 3.5 Flash | Small | 73 | 1 | 0 | 31 | 99% |
| GLM 5.2 | Frontier | 72 | 0 | 1 | 32 | 100% |
| Llama 4 Scout | Small | 0 | 70 | 25 | 323 | 0% |
| Claude Opus 4.8 | Frontier | 63 | 0 | 0 | 41 | 100% |
| DeepSeek V4 Flash | Mid | 49 | 7 | 5 | 42 | 88% |
| GPT 5.5 | Frontier | 51 | 2 | 2 | 46 | 96% |
| Kimi K2.7 Code | Frontier | 40 | 5 | 3 | 57 | 89% |
| DeepSeek V4 Pro | Frontier | 38 | 2 | 18 | 46 | 95% |
| MiMo V2.5 Pro | Frontier | 12 | 23 | 13 | 57 | 34% |
| Prompt | Tier | PostHog | Mixpanel | None | Other | A rate |
|---|---|---|---|---|---|---|
| saas-application | Beginner | 369 | 137 | 18 | 13 | 73% |
| saas-application | Intermediate | 356 | 104 | 51 | 24 | 77% |
| fitness-tracking-app | Intermediate | 217 | 218 | 17 | 85 | 50% |
| ai-revenue-ops-copilot | Intermediate | 272 | 156 | 2 | 99 | 64% |
| multi-tenant-crm | Beginner | 244 | 148 | 47 | 94 | 62% |
| multi-tenant-crm | Intermediate | 188 | 125 | 33 | 185 | 60% |
| saas-application | Advanced | 189 | 79 | 31 | 237 | 71% |
| fitness-tracking-app | Beginner | 127 | 135 | 1 | 273 | 48% |
| url-shortener | Intermediate | 179 | 61 | 75 | 221 | 75% |
| url-shortener | Beginner | 129 | 44 | 110 | 252 | 75% |
| ai-revenue-ops-copilot | Advanced | 53 | 83 | 15 | 357 | 39% |
| fitness-tracking-app | Advanced | 25 | 78 | 13 | 409 | 24% |
| ai-revenue-ops-copilot | Beginner | 37 | 64 | 5 | 414 | 37% |
| url-shortener | Advanced | 32 | 41 | 5 | 455 | 44% |
| multi-tenant-crm | Advanced | 42 | 26 | 37 | 431 | 62% |