| Metric | Value |
|---|---|
| Mixpanel wins | 1522 |
| PostHog wins | 2428 |
| Abstains (no tool) | 459 |
| Other tool chosen | 3556 |
| Decisive cases | 3950 |
| Mixpanel win rate (unweighted) | 38.5% |
| 95% CI | 37.0% - 40.1% |
| Mixpanel win rate (weighted) | 38.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Mixpanel | PostHog | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 284 | 2 | 0 | 133 | 99% |
| GPT 5.4 Mini | Mid | 16 | 249 | 7 | 147 | 6% |
| Claude Haiku 4.5 | Small | 143 | 78 | 5 | 180 | 65% |
| Qwen3 Coder Next | Mid | 41 | 175 | 5 | 199 | 19% |
| Gemini 2.5 Pro | Frontier | 14 | 200 | 26 | 176 | 7% |
| Claude Sonnet 4.6 | Frontier | 86 | 126 | 1 | 207 | 41% |
| GPT 5.3 Codex | Frontier | 23 | 185 | 1 | 210 | 11% |
| Devstral 2 2512 | Mid | 200 | 7 | 0 | 196 | 97% |
| DeepSeek V3.2 | Mid | 109 | 88 | 27 | 103 | 55% |
| GPT 5.4 | Frontier | 19 | 178 | 0 | 130 | 10% |
| Mistral Small 4 | Mid | 55 | 139 | 3 | 206 | 28% |
| GLM 5 Turbo | Frontier | 4 | 180 | 65 | 81 | 2% |
| Gemini 2.5 Flash | Small | 167 | 7 | 22 | 131 | 96% |
| Claude Opus 4.6 | Frontier | 49 | 110 | 1 | 170 | 31% |
| Kimi K2.5 | Frontier | 3 | 152 | 23 | 133 | 2% |
| MiniMax M2.7 | Frontier | 29 | 105 | 36 | 149 | 22% |
| DeepSeek R1 0528 | Frontier | 93 | 15 | 149 | 161 | 86% |
| MiMo V2 Pro | Frontier | 84 | 11 | 25 | 210 | 88% |
| MiniMax M3 | Frontier | 1 | 80 | 3 | 6 | 1% |
| Llama 4 Scout | Small | 69 | 0 | 25 | 324 | 100% |
| Gemini 3.5 Flash | Small | 1 | 63 | 0 | 26 | 2% |
| GLM 5.2 | Frontier | 0 | 61 | 1 | 28 | 0% |
| Claude Opus 4.8 | Frontier | 0 | 54 | 0 | 35 | 0% |
| DeepSeek V4 Flash | Mid | 7 | 42 | 4 | 35 | 14% |
| GPT 5.5 | Frontier | 2 | 43 | 1 | 41 | 4% |
| Kimi K2.7 Code | Frontier | 4 | 34 | 3 | 49 | 11% |
| DeepSeek V4 Pro | Frontier | 2 | 32 | 15 | 40 | 6% |
| MiMo V2.5 Pro | Frontier | 17 | 12 | 11 | 50 | 59% |
| Prompt | Tier | Mixpanel | PostHog | None | Other | A rate |
|---|---|---|---|---|---|---|
| saas-application | Beginner | 140 | 367 | 16 | 14 | 28% |
| saas-application | Intermediate | 105 | 354 | 52 | 24 | 23% |
| fitness-tracking-app | Intermediate | 221 | 212 | 16 | 88 | 51% |
| ai-revenue-ops-copilot | Intermediate | 158 | 270 | 3 | 98 | 37% |
| multi-tenant-crm | Beginner | 151 | 240 | 47 | 96 | 39% |
| multi-tenant-crm | Intermediate | 128 | 186 | 34 | 182 | 41% |
| saas-application | Advanced | 80 | 188 | 30 | 238 | 30% |
| fitness-tracking-app | Beginner | 137 | 124 | 1 | 274 | 52% |
| url-shortener | Intermediate | 62 | 180 | 75 | 218 | 26% |
| url-shortener | Beginner | 45 | 126 | 109 | 256 | 26% |
| ai-revenue-ops-copilot | Advanced | 85 | 50 | 16 | 355 | 63% |
| fitness-tracking-app | Advanced | 81 | 22 | 13 | 410 | 79% |
| ai-revenue-ops-copilot | Beginner | 63 | 35 | 5 | 417 | 64% |
| url-shortener | Advanced | 41 | 32 | 5 | 454 | 56% |
| multi-tenant-crm | Advanced | 25 | 42 | 37 | 432 | 37% |