| Metric | Value |
|---|---|
| Amplitude wins | 121 |
| Tinybird wins | 129 |
| Abstains (no tool) | 364 |
| Other tool chosen | 5300 |
| Decisive cases | 250 |
| Amplitude win rate (unweighted) | 48.4% |
| 95% CI | 42.3% - 54.6% |
| Amplitude win rate (weighted) | 48.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Amplitude | Tinybird | None | Other | A rate |
|---|---|---|---|---|---|---|
| Gemini 2.5 Pro | Frontier | 0 | 54 | 23 | 235 | 0% |
| Claude Sonnet 4.6 | Frontier | 1 | 39 | 1 | 274 | 3% |
| Kimi K2.5 | Frontier | 6 | 26 | 22 | 243 | 19% |
| GPT 5.4 Mini | Mid | 28 | 0 | 5 | 282 | 100% |
| Gemini 2.5 Flash | Small | 23 | 0 | 21 | 268 | 100% |
| MiMo V2 Pro | Frontier | 21 | 0 | 24 | 270 | 100% |
| GPT 5.3 Codex | Frontier | 11 | 0 | 1 | 302 | 100% |
| MiniMax M2.7 | Frontier | 9 | 1 | 34 | 260 | 90% |
| DeepSeek R1 0528 | Frontier | 8 | 0 | 114 | 191 | 100% |
| Mistral Small 4 | Mid | 8 | 0 | 2 | 291 | 100% |
| DeepSeek V3.2 | Mid | 1 | 4 | 26 | 282 | 20% |
| Qwen3 Coder Next | Mid | 3 | 0 | 5 | 307 | 100% |
| Claude Opus 4.6 | Frontier | 0 | 3 | 1 | 311 | 0% |
| GLM 5 Turbo | Frontier | 0 | 2 | 61 | 252 | 0% |
| Devstral 2 2512 | Mid | 1 | 0 | 0 | 312 | 100% |
| GPT 5.4 | Frontier | 1 | 0 | 0 | 311 | 100% |
| Claude Haiku 4.5 | Small | 0 | 0 | 4 | 301 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 0 | 314 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 20 | 294 | n/a |
| Prompt | Tier | Amplitude | Tinybird | None | Other | A rate |
|---|---|---|---|---|---|---|
| url-shortener | Intermediate | 2 | 49 | 55 | 291 | 4% |
| url-shortener | Beginner | 0 | 51 | 84 | 263 | 0% |
| fitness-tracking-app | Advanced | 34 | 2 | 9 | 347 | 94% |
| ai-revenue-ops-copilot | Advanced | 25 | 0 | 14 | 338 | 100% |
| ai-revenue-ops-copilot | Intermediate | 24 | 0 | 3 | 365 | 100% |
| url-shortener | Advanced | 1 | 19 | 4 | 371 | 5% |
| fitness-tracking-app | Beginner | 13 | 0 | 1 | 384 | 100% |
| fitness-tracking-app | Intermediate | 12 | 0 | 12 | 375 | 100% |
| multi-tenant-crm | Advanced | 0 | 8 | 31 | 359 | 0% |
| saas-application | Advanced | 7 | 0 | 25 | 366 | 100% |
| saas-application | Intermediate | 2 | 0 | 45 | 350 | 100% |
| ai-revenue-ops-copilot | Beginner | 1 | 0 | 5 | 379 | 100% |
| multi-tenant-crm | Beginner | 0 | 0 | 35 | 362 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 28 | 364 | n/a |
| saas-application | Beginner | 0 | 0 | 13 | 386 | n/a |