| Metric | Value |
|---|---|
| Amplitude wins | 141 |
| Tinybird wins | 148 |
| Abstains (no tool) | 530 |
| Other tool chosen | 6810 |
| Decisive cases | 289 |
| Amplitude win rate (unweighted) | 48.8% |
| 95% CI | 43.1% - 54.5% |
| Amplitude win rate (weighted) | 48.8% |
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 | 64 | 36 | 300 | 0% |
| Claude Sonnet 4.6 | Frontier | 1 | 44 | 1 | 359 | 2% |
| GPT 5.4 Mini | Mid | 34 | 0 | 5 | 366 | 100% |
| Kimi K2.5 | Frontier | 8 | 26 | 33 | 303 | 24% |
| Gemini 2.5 Flash | Small | 24 | 0 | 30 | 333 | 100% |
| MiMo V2 Pro | Frontier | 24 | 0 | 34 | 332 | 100% |
| GPT 5.3 Codex | Frontier | 12 | 0 | 10 | 382 | 100% |
| MiniMax M2.7 | Frontier | 10 | 1 | 52 | 316 | 91% |
| Mistral Small 4 | Mid | 9 | 0 | 2 | 378 | 100% |
| DeepSeek R1 0528 | Frontier | 8 | 0 | 148 | 247 | 100% |
| Qwen3 Coder Next | Mid | 5 | 0 | 8 | 392 | 100% |
| DeepSeek V3.2 | Mid | 1 | 4 | 33 | 349 | 20% |
| GLM 5 Turbo | Frontier | 1 | 2 | 81 | 306 | 33% |
| Claude Opus 4.6 | Frontier | 0 | 3 | 9 | 378 | 0% |
| DeepSeek V4 Flash | Mid | 1 | 1 | 2 | 11 | 50% |
| Gemini 3.5 Flash | Small | 0 | 2 | 0 | 13 | 0% |
| Devstral 2 2512 | Mid | 1 | 0 | 3 | 399 | 100% |
| GPT 5.4 | Frontier | 1 | 0 | 2 | 384 | 100% |
| Kimi K2.7 Code | Frontier | 1 | 0 | 0 | 14 | 100% |
| DeepSeek V4 Pro | Frontier | 0 | 1 | 3 | 10 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 15 | 379 | n/a |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 15 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 0 | 15 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 0 | 14 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 0 | 404 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 21 | 383 | n/a |
| MiMo V2.5 Pro | Frontier | 0 | 0 | 2 | 13 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 0 | 15 | n/a |
| Prompt | Tier | Amplitude | Tinybird | None | Other | A rate |
|---|---|---|---|---|---|---|
| url-shortener | Intermediate | 2 | 54 | 62 | 318 | 4% |
| url-shortener | Beginner | 0 | 54 | 91 | 292 | 0% |
| fitness-tracking-app | Advanced | 38 | 3 | 11 | 378 | 93% |
| ai-revenue-ops-copilot | Advanced | 27 | 0 | 14 | 372 | 100% |
| ai-revenue-ops-copilot | Intermediate | 27 | 0 | 3 | 401 | 100% |
| url-shortener | Advanced | 1 | 22 | 4 | 407 | 4% |
| fitness-tracking-app | Beginner | 14 | 0 | 1 | 422 | 100% |
| fitness-tracking-app | Intermediate | 13 | 0 | 14 | 411 | 100% |
| saas-application | Advanced | 8 | 1 | 26 | 402 | 89% |
| multi-tenant-crm | Advanced | 0 | 8 | 33 | 396 | 0% |
| fitness-tracking-app | Beginner | 3 | 0 | 1 | 91 | 100% |
| multi-tenant-crm | Advanced | 0 | 3 | 5 | 87 | 0% |
| saas-application | Advanced | 2 | 0 | 6 | 87 | 100% |
| saas-application | Intermediate | 2 | 0 | 47 | 387 | 100% |
| url-shortener | Beginner | 0 | 2 | 40 | 53 | 0% |
| ai-revenue-ops-copilot | Beginner | 1 | 0 | 5 | 416 | 100% |
| fitness-tracking-app | Advanced | 1 | 0 | 3 | 89 | 100% |
| fitness-tracking-app | Intermediate | 1 | 0 | 10 | 84 | 100% |
| multi-tenant-crm | Beginner | 1 | 0 | 38 | 396 | 100% |
| url-shortener | Advanced | 0 | 1 | 4 | 90 | 0% |
| multi-tenant-crm | Beginner | 0 | 0 | 16 | 79 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 19 | 76 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 29 | 402 | n/a |
| saas-application | Intermediate | 0 | 0 | 4 | 91 | n/a |
| saas-application | Beginner | 0 | 0 | 4 | 91 | n/a |
| saas-application | Beginner | 0 | 0 | 14 | 424 | n/a |
| url-shortener | Intermediate | 0 | 0 | 26 | 68 | n/a |