| Metric | Value |
|---|---|
| Mixpanel wins | 517 |
| PostHog wins | 719 |
| Abstains (no tool) | 151 |
| Other tool chosen | 1145 |
| Decisive cases | 1236 |
| Mixpanel win rate (unweighted) | 41.8% |
| 95% CI | 39.1% - 44.6% |
| Mixpanel win rate (weighted) | 41.8% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Mixpanel | PostHog | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 95 | 1 | 0 | 39 | 99% |
| GPT 5.4 Mini | Mid | 4 | 83 | 2 | 46 | 5% |
| DeepSeek V3.2 | Mid | 46 | 39 | 8 | 41 | 54% |
| GPT 5.4 | Frontier | 8 | 71 | 0 | 55 | 10% |
| Devstral 2 2512 | Mid | 74 | 2 | 0 | 58 | 97% |
| Gemini 2.5 Flash | Small | 73 | 2 | 9 | 49 | 97% |
| GLM 5 Turbo | Frontier | 2 | 73 | 24 | 36 | 3% |
| Claude Haiku 4.5 | Small | 42 | 26 | 1 | 61 | 62% |
| Claude Sonnet 4.6 | Frontier | 27 | 41 | 0 | 67 | 40% |
| Gemini 2.5 Pro | Frontier | 3 | 65 | 9 | 56 | 4% |
| Qwen3 Coder Next | Mid | 12 | 54 | 2 | 66 | 18% |
| GPT 5.3 Codex | Frontier | 5 | 61 | 0 | 68 | 8% |
| Claude Opus 4.6 | Frontier | 22 | 40 | 0 | 73 | 35% |
| Mistral Small 4 | Mid | 17 | 45 | 1 | 68 | 27% |
| Kimi K2.5 | Frontier | 1 | 60 | 12 | 50 | 2% |
| MiniMax M2.7 | Frontier | 10 | 46 | 14 | 64 | 18% |
| MiMo V2 Pro | Frontier | 33 | 4 | 10 | 88 | 89% |
| DeepSeek R1 0528 | Frontier | 30 | 6 | 49 | 49 | 83% |
| Llama 4 Scout | Small | 13 | 0 | 10 | 111 | 100% |
| Prompt | Tier | Mixpanel | PostHog | None | Other | A rate |
|---|---|---|---|---|---|---|
| saas-application | Beginner | 45 | 113 | 5 | 8 | 28% |
| saas-application | Intermediate | 31 | 112 | 20 | 8 | 22% |
| fitness-tracking-app | Intermediate | 74 | 63 | 4 | 30 | 54% |
| ai-revenue-ops-copilot | Intermediate | 51 | 83 | 1 | 34 | 38% |
| multi-tenant-crm | Beginner | 52 | 73 | 13 | 33 | 42% |
| multi-tenant-crm | Intermediate | 47 | 55 | 11 | 53 | 46% |
| saas-application | Advanced | 26 | 63 | 9 | 73 | 29% |
| fitness-tracking-app | Beginner | 44 | 39 | 1 | 86 | 53% |
| url-shortener | Intermediate | 25 | 47 | 26 | 72 | 35% |
| url-shortener | Beginner | 18 | 31 | 35 | 87 | 37% |
| ai-revenue-ops-copilot | Advanced | 26 | 10 | 4 | 119 | 72% |
| fitness-tracking-app | Advanced | 31 | 2 | 2 | 132 | 94% |
| ai-revenue-ops-copilot | Beginner | 24 | 6 | 3 | 134 | 80% |
| url-shortener | Advanced | 18 | 10 | 2 | 137 | 64% |
| multi-tenant-crm | Advanced | 5 | 12 | 15 | 139 | 29% |