| Metric | Value |
|---|---|
| Amplitude wins | 177 |
| Tinybird wins | 222 |
| Abstains (no tool) | 748 |
| Other tool chosen | 9641 |
| Decisive cases | 399 |
| Amplitude win rate (unweighted) | 44.4% |
| 95% CI | 39.6% - 49.3% |
| Amplitude win rate (weighted) | 44.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Amplitude | Tinybird | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 2 | 5 | 47 | 508 | 29% |
| DeepSeek Pro 4–4 0813 | Frontier | 1 | 6 | 19 | 108 | 14% |
| DeepSeek R1 | Frontier | 13 | 1 | 205 | 346 | 93% |
| Devstral | Mid | 4 | 0 | 6 | 525 | 100% |
| Gemini Flash 2.5–3.8 | Small | 24 | 21 | 35 | 485 | 53% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 0 | 87 | 48 | 427 | 0% |
| GLM 5 Turbo–5.3 | Frontier | 1 | 2 | 91 | 474 | 33% |
| GPT 5.4–6 Astra | Frontier | 2 | 5 | 12 | 540 | 29% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 15 | 0 | 18 | 534 | 100% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 43 | 0 | 11 | 511 | 100% |
| Haiku | Small | 0 | 0 | 24 | 529 | n/a |
| Kimi 2.5–3 | Frontier | 18 | 31 | 42 | 457 | 37% |
| Llama Maverick | Frontier | 0 | 0 | 0 | 567 | n/a |
| Llama Scout | Small | 0 | 0 | 29 | 537 | n/a |
| MiMo Pro 2–2.6 | Frontier | 27 | 1 | 55 | 482 | 96% |
| MiniMax M 2.7–3 | Frontier | 10 | 1 | 68 | 478 | 91% |
| Mistral Small | Mid | 11 | 0 | 3 | 535 | 100% |
| Opus 4.6–5.5 | Frontier | 0 | 4 | 17 | 546 | 0% |
| Qwen Coder | Mid | 5 | 0 | 8 | 553 | 100% |
| Sonnet 4.6–5.5 | Frontier | 1 | 58 | 10 | 499 | 2% |
| Prompt | Tier | Amplitude | Tinybird | None | Other | A rate |
|---|---|---|---|---|---|---|
| url-shortener | Intermediate | 2 | 83 | 85 | 424 | 2% |
| url-shortener | Beginner | 1 | 74 | 132 | 387 | 1% |
| fitness-tracking-app | Advanced | 43 | 5 | 15 | 518 | 90% |
| ai-revenue-ops-copilot | Intermediate | 39 | 0 | 3 | 545 | 100% |
| url-shortener | Advanced | 4 | 30 | 5 | 552 | 12% |
| ai-revenue-ops-copilot | Advanced | 32 | 1 | 16 | 515 | 97% |
| fitness-tracking-app | Beginner | 19 | 0 | 1 | 575 | 100% |
| fitness-tracking-app | Intermediate | 13 | 0 | 19 | 564 | 100% |
| saas-application | Advanced | 10 | 2 | 33 | 550 | 83% |
| multi-tenant-crm | Advanced | 0 | 10 | 38 | 547 | 0% |
| multi-tenant-crm | Advanced | 0 | 6 | 8 | 156 | 0% |
| saas-application | Intermediate | 3 | 2 | 57 | 532 | 60% |
| fitness-tracking-app | Beginner | 3 | 0 | 2 | 165 | 100% |
| saas-application | Advanced | 3 | 0 | 9 | 158 | 100% |
| fitness-tracking-app | Advanced | 2 | 1 | 3 | 163 | 67% |
| url-shortener | Advanced | 0 | 3 | 5 | 143 | 0% |
| url-shortener | Beginner | 0 | 2 | 62 | 88 | 0% |
| url-shortener | Intermediate | 0 | 2 | 49 | 100 | 0% |
| ai-revenue-ops-copilot | Beginner | 1 | 0 | 5 | 574 | 100% |
| fitness-tracking-app | Intermediate | 1 | 0 | 20 | 131 | 100% |
| multi-tenant-crm | Beginner | 1 | 0 | 57 | 534 | 100% |
| multi-tenant-crm | Intermediate | 0 | 1 | 37 | 551 | 0% |
| multi-tenant-crm | Beginner | 0 | 0 | 31 | 137 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 25 | 127 | n/a |
| saas-application | Intermediate | 0 | 0 | 7 | 164 | n/a |
| saas-application | Beginner | 0 | 0 | 18 | 578 | n/a |
| saas-application | Beginner | 0 | 0 | 6 | 163 | n/a |