| Metric | Value |
|---|---|
| Mixpanel wins | 1499 |
| PostHog wins | 2459 |
| Abstains (no tool) | 460 |
| Other tool chosen | 3549 |
| Decisive cases | 3958 |
| Mixpanel win rate (unweighted) | 37.9% |
| 95% CI | 36.4% - 39.4% |
| Mixpanel win rate (weighted) | 37.9% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Mixpanel | PostHog | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 282 | 1 | 0 | 136 | 100% |
| GPT 5.4 Mini | Mid | 16 | 249 | 7 | 147 | 6% |
| Claude Haiku 4.5 | Small | 146 | 76 | 6 | 179 | 66% |
| Qwen3 Coder Next | Mid | 40 | 177 | 5 | 197 | 18% |
| Gemini 2.5 Pro | Frontier | 14 | 202 | 23 | 177 | 6% |
| Claude Sonnet 4.6 | Frontier | 86 | 127 | 1 | 206 | 40% |
| GPT 5.3 Codex | Frontier | 25 | 183 | 1 | 210 | 12% |
| Devstral 2 2512 | Mid | 191 | 6 | 0 | 191 | 97% |
| Mistral Small 4 | Mid | 55 | 139 | 3 | 205 | 28% |
| GPT 5.4 | Frontier | 19 | 170 | 0 | 123 | 10% |
| DeepSeek V3.2 | Mid | 104 | 84 | 26 | 98 | 55% |
| GLM 5 Turbo | Frontier | 3 | 172 | 63 | 77 | 2% |
| Gemini 2.5 Flash | Small | 161 | 5 | 21 | 125 | 97% |
| Claude Opus 4.6 | Frontier | 46 | 106 | 1 | 162 | 30% |
| Kimi K2.5 | Frontier | 3 | 145 | 23 | 129 | 2% |
| MiniMax M2.7 | Frontier | 26 | 101 | 36 | 141 | 20% |
| DeepSeek R1 0528 | Frontier | 90 | 15 | 150 | 163 | 86% |
| MiniMax M3 | Frontier | 1 | 93 | 3 | 8 | 1% |
| MiMo V2 Pro | Frontier | 81 | 10 | 24 | 200 | 89% |
| Gemini 3.5 Flash | Small | 1 | 73 | 0 | 31 | 1% |
| GLM 5.2 | Frontier | 0 | 72 | 1 | 32 | 0% |
| Llama 4 Scout | Small | 70 | 0 | 25 | 323 | 100% |
| Claude Opus 4.8 | Frontier | 0 | 63 | 0 | 41 | 0% |
| DeepSeek V4 Flash | Mid | 7 | 49 | 5 | 42 | 13% |
| GPT 5.5 | Frontier | 2 | 51 | 2 | 46 | 4% |
| Kimi K2.7 Code | Frontier | 5 | 40 | 3 | 57 | 11% |
| DeepSeek V4 Pro | Frontier | 2 | 38 | 18 | 46 | 5% |
| MiMo V2.5 Pro | Frontier | 23 | 12 | 13 | 57 | 66% |
| Prompt | Tier | Mixpanel | PostHog | None | Other | A rate |
|---|---|---|---|---|---|---|
| saas-application | Beginner | 137 | 369 | 18 | 13 | 27% |
| saas-application | Intermediate | 104 | 356 | 51 | 24 | 23% |
| fitness-tracking-app | Intermediate | 218 | 217 | 17 | 85 | 50% |
| ai-revenue-ops-copilot | Intermediate | 156 | 272 | 2 | 99 | 36% |
| multi-tenant-crm | Beginner | 148 | 244 | 47 | 94 | 38% |
| multi-tenant-crm | Intermediate | 125 | 188 | 33 | 185 | 40% |
| saas-application | Advanced | 79 | 189 | 31 | 237 | 29% |
| fitness-tracking-app | Beginner | 135 | 127 | 1 | 273 | 52% |
| url-shortener | Intermediate | 61 | 179 | 75 | 221 | 25% |
| url-shortener | Beginner | 44 | 129 | 110 | 252 | 25% |
| ai-revenue-ops-copilot | Advanced | 83 | 53 | 15 | 357 | 61% |
| fitness-tracking-app | Advanced | 78 | 25 | 13 | 409 | 76% |
| ai-revenue-ops-copilot | Beginner | 64 | 37 | 5 | 414 | 63% |
| url-shortener | Advanced | 41 | 32 | 5 | 455 | 56% |
| multi-tenant-crm | Advanced | 26 | 42 | 37 | 431 | 38% |