| Metric | Value |
|---|---|
| PostHog wins | 2231 |
| Mixpanel wins | 1456 |
| Abstains (no tool) | 530 |
| Other tool chosen | 3412 |
| Decisive cases | 3687 |
| PostHog win rate (unweighted) | 60.5% |
| 95% CI | 58.9% - 62.1% |
| PostHog win rate (weighted) | 60.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | PostHog | Mixpanel | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 5 | 267 | 0 | 132 | 2% |
| GPT 5.4 Mini | Mid | 242 | 14 | 5 | 144 | 95% |
| GPT 5.4 | Frontier | 221 | 20 | 2 | 144 | 92% |
| DeepSeek V3.2 | Mid | 108 | 120 | 33 | 126 | 47% |
| GLM 5 Turbo | Frontier | 211 | 4 | 81 | 94 | 98% |
| Gemini 2.5 Pro | Frontier | 194 | 11 | 36 | 159 | 95% |
| Claude Haiku 4.5 | Small | 88 | 117 | 15 | 174 | 43% |
| Claude Sonnet 4.6 | Frontier | 118 | 85 | 1 | 201 | 58% |
| Qwen3 Coder Next | Mid | 167 | 34 | 8 | 196 | 83% |
| Gemini 2.5 Flash | Small | 13 | 188 | 30 | 156 | 6% |
| GPT 5.3 Codex | Frontier | 182 | 17 | 10 | 195 | 91% |
| Devstral 2 2512 | Mid | 12 | 186 | 3 | 202 | 6% |
| Kimi K2.5 | Frontier | 186 | 3 | 33 | 148 | 98% |
| Mistral Small 4 | Mid | 137 | 51 | 2 | 199 | 73% |
| Claude Opus 4.6 | Frontier | 124 | 59 | 9 | 198 | 68% |
| MiniMax M2.7 | Frontier | 126 | 31 | 52 | 170 | 80% |
| MiMo V2 Pro | Frontier | 14 | 101 | 34 | 241 | 12% |
| DeepSeek R1 0528 | Frontier | 13 | 90 | 148 | 152 | 13% |
| Llama 4 Scout | Small | 0 | 54 | 21 | 329 | 0% |
| MiniMax M3 | Frontier | 14 | 0 | 0 | 1 | 100% |
| Gemini 3.5 Flash | Small | 12 | 0 | 0 | 3 | 100% |
| GLM 5.2 | Frontier | 10 | 0 | 0 | 5 | 100% |
| Claude Opus 4.8 | Frontier | 9 | 0 | 0 | 6 | 100% |
| Kimi K2.7 Code | Frontier | 7 | 1 | 0 | 7 | 88% |
| GPT 5.5 | Frontier | 7 | 0 | 0 | 7 | 100% |
| DeepSeek V4 Flash | Mid | 5 | 2 | 2 | 6 | 71% |
| MiMo V2.5 Pro | Frontier | 3 | 1 | 2 | 9 | 75% |
| DeepSeek V4 Pro | Frontier | 3 | 0 | 3 | 8 | 100% |
| Prompt | Tier | PostHog | Mixpanel | None | Other | A rate |
|---|---|---|---|---|---|---|
| saas-application | Beginner | 291 | 121 | 14 | 12 | 71% |
| saas-application | Intermediate | 280 | 88 | 47 | 21 | 76% |
| fitness-tracking-app | Intermediate | 154 | 195 | 14 | 75 | 44% |
| ai-revenue-ops-copilot | Intermediate | 212 | 136 | 3 | 80 | 61% |
| multi-tenant-crm | Beginner | 186 | 130 | 38 | 81 | 59% |
| multi-tenant-crm | Intermediate | 147 | 114 | 29 | 141 | 56% |
| saas-application | Advanced | 146 | 65 | 26 | 200 | 69% |
| fitness-tracking-app | Beginner | 95 | 113 | 1 | 228 | 46% |
| url-shortener | Intermediate | 139 | 57 | 62 | 178 | 71% |
| url-shortener | Beginner | 92 | 41 | 91 | 213 | 69% |
| ai-revenue-ops-copilot | Advanced | 35 | 75 | 14 | 289 | 32% |
| ai-revenue-ops-copilot | Beginner | 24 | 56 | 5 | 337 | 30% |
| saas-application | Beginner | 59 | 20 | 4 | 12 | 75% |
| saas-application | Intermediate | 70 | 7 | 4 | 14 | 91% |
| fitness-tracking-app | Advanced | 9 | 66 | 11 | 344 | 12% |
| fitness-tracking-app | Intermediate | 42 | 24 | 10 | 19 | 64% |
| url-shortener | Advanced | 24 | 36 | 4 | 370 | 40% |
| multi-tenant-crm | Advanced | 32 | 22 | 33 | 350 | 59% |
| fitness-tracking-app | Beginner | 30 | 21 | 1 | 43 | 59% |
| multi-tenant-crm | Beginner | 39 | 11 | 16 | 29 | 78% |
| saas-application | Advanced | 31 | 15 | 6 | 43 | 67% |
| multi-tenant-crm | Intermediate | 31 | 8 | 19 | 37 | 79% |
| url-shortener | Intermediate | 31 | 7 | 26 | 30 | 82% |
| multi-tenant-crm | Advanced | 10 | 13 | 5 | 67 | 43% |
| fitness-tracking-app | Advanced | 9 | 13 | 3 | 68 | 41% |
| url-shortener | Beginner | 12 | 0 | 40 | 43 | 100% |
| url-shortener | Advanced | 1 | 2 | 4 | 88 | 33% |