| Metric | Value |
|---|---|
| Mixpanel wins | 1456 |
| PostHog wins | 2231 |
| Abstains (no tool) | 530 |
| Other tool chosen | 3412 |
| Decisive cases | 3687 |
| Mixpanel win rate (unweighted) | 39.5% |
| 95% CI | 37.9% - 41.1% |
| Mixpanel win rate (weighted) | 39.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Mixpanel | PostHog | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 267 | 5 | 0 | 132 | 98% |
| GPT 5.4 Mini | Mid | 14 | 242 | 5 | 144 | 5% |
| GPT 5.4 | Frontier | 20 | 221 | 2 | 144 | 8% |
| DeepSeek V3.2 | Mid | 120 | 108 | 33 | 126 | 53% |
| GLM 5 Turbo | Frontier | 4 | 211 | 81 | 94 | 2% |
| Claude Haiku 4.5 | Small | 117 | 88 | 15 | 174 | 57% |
| Gemini 2.5 Pro | Frontier | 11 | 194 | 36 | 159 | 5% |
| Claude Sonnet 4.6 | Frontier | 85 | 118 | 1 | 201 | 42% |
| Gemini 2.5 Flash | Small | 188 | 13 | 30 | 156 | 94% |
| Qwen3 Coder Next | Mid | 34 | 167 | 8 | 196 | 17% |
| GPT 5.3 Codex | Frontier | 17 | 182 | 10 | 195 | 9% |
| Devstral 2 2512 | Mid | 186 | 12 | 3 | 202 | 94% |
| Kimi K2.5 | Frontier | 3 | 186 | 33 | 148 | 2% |
| Mistral Small 4 | Mid | 51 | 137 | 2 | 199 | 27% |
| Claude Opus 4.6 | Frontier | 59 | 124 | 9 | 198 | 32% |
| MiniMax M2.7 | Frontier | 31 | 126 | 52 | 170 | 20% |
| MiMo V2 Pro | Frontier | 101 | 14 | 34 | 241 | 88% |
| DeepSeek R1 0528 | Frontier | 90 | 13 | 148 | 152 | 87% |
| Llama 4 Scout | Small | 54 | 0 | 21 | 329 | 100% |
| MiniMax M3 | Frontier | 0 | 14 | 0 | 1 | 0% |
| Gemini 3.5 Flash | Small | 0 | 12 | 0 | 3 | 0% |
| GLM 5.2 | Frontier | 0 | 10 | 0 | 5 | 0% |
| Claude Opus 4.8 | Frontier | 0 | 9 | 0 | 6 | 0% |
| Kimi K2.7 Code | Frontier | 1 | 7 | 0 | 7 | 13% |
| DeepSeek V4 Flash | Mid | 2 | 5 | 2 | 6 | 29% |
| GPT 5.5 | Frontier | 0 | 7 | 0 | 7 | 0% |
| MiMo V2.5 Pro | Frontier | 1 | 3 | 2 | 9 | 25% |
| DeepSeek V4 Pro | Frontier | 0 | 3 | 3 | 8 | 0% |
| Prompt | Tier | Mixpanel | PostHog | None | Other | A rate |
|---|---|---|---|---|---|---|
| saas-application | Beginner | 121 | 291 | 14 | 12 | 29% |
| saas-application | Intermediate | 88 | 280 | 47 | 21 | 24% |
| fitness-tracking-app | Intermediate | 195 | 154 | 14 | 75 | 56% |
| ai-revenue-ops-copilot | Intermediate | 136 | 212 | 3 | 80 | 39% |
| multi-tenant-crm | Beginner | 130 | 186 | 38 | 81 | 41% |
| multi-tenant-crm | Intermediate | 114 | 147 | 29 | 141 | 44% |
| saas-application | Advanced | 65 | 146 | 26 | 200 | 31% |
| fitness-tracking-app | Beginner | 113 | 95 | 1 | 228 | 54% |
| url-shortener | Intermediate | 57 | 139 | 62 | 178 | 29% |
| url-shortener | Beginner | 41 | 92 | 91 | 213 | 31% |
| ai-revenue-ops-copilot | Advanced | 75 | 35 | 14 | 289 | 68% |
| ai-revenue-ops-copilot | Beginner | 56 | 24 | 5 | 337 | 70% |
| saas-application | Beginner | 20 | 59 | 4 | 12 | 25% |
| saas-application | Intermediate | 7 | 70 | 4 | 14 | 9% |
| fitness-tracking-app | Advanced | 66 | 9 | 11 | 344 | 88% |
| fitness-tracking-app | Intermediate | 24 | 42 | 10 | 19 | 36% |
| url-shortener | Advanced | 36 | 24 | 4 | 370 | 60% |
| multi-tenant-crm | Advanced | 22 | 32 | 33 | 350 | 41% |
| fitness-tracking-app | Beginner | 21 | 30 | 1 | 43 | 41% |
| multi-tenant-crm | Beginner | 11 | 39 | 16 | 29 | 22% |
| saas-application | Advanced | 15 | 31 | 6 | 43 | 33% |
| multi-tenant-crm | Intermediate | 8 | 31 | 19 | 37 | 21% |
| url-shortener | Intermediate | 7 | 31 | 26 | 30 | 18% |
| multi-tenant-crm | Advanced | 13 | 10 | 5 | 67 | 57% |
| fitness-tracking-app | Advanced | 13 | 9 | 3 | 68 | 59% |
| url-shortener | Beginner | 0 | 12 | 40 | 43 | 0% |
| url-shortener | Advanced | 2 | 1 | 4 | 88 | 67% |