| Metric | Value |
|---|---|
| Amplitude wins | 155 |
| Tinybird wins | 192 |
| Abstains (no tool) | 459 |
| Other tool chosen | 7159 |
| Decisive cases | 347 |
| Amplitude win rate (unweighted) | 44.7% |
| 95% CI | 39.5% - 49.9% |
| Amplitude win rate (weighted) | 44.7% |
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 | 73 | 26 | 317 | 0% |
| Claude Sonnet 4.6 | Frontier | 1 | 53 | 1 | 365 | 2% |
| GPT 5.4 Mini | Mid | 39 | 0 | 7 | 373 | 100% |
| Kimi K2.5 | Frontier | 8 | 26 | 23 | 254 | 24% |
| Gemini 2.5 Flash | Small | 24 | 0 | 22 | 281 | 100% |
| MiMo V2 Pro | Frontier | 22 | 0 | 25 | 283 | 100% |
| Gemini 3.5 Flash | Small | 0 | 17 | 0 | 73 | 0% |
| GPT 5.3 Codex | Frontier | 15 | 0 | 1 | 403 | 100% |
| Kimi K2.7 Code | Frontier | 7 | 4 | 3 | 76 | 64% |
| DeepSeek R1 0528 | Frontier | 10 | 0 | 149 | 259 | 100% |
| MiniMax M2.7 | Frontier | 9 | 1 | 36 | 273 | 90% |
| Mistral Small 4 | Mid | 8 | 0 | 3 | 392 | 100% |
| DeepSeek V4 Pro | Frontier | 1 | 5 | 15 | 68 | 17% |
| DeepSeek V3.2 | Mid | 1 | 4 | 27 | 295 | 20% |
| GPT 5.5 | Frontier | 1 | 3 | 1 | 82 | 25% |
| MiMo V2.5 Pro | Frontier | 3 | 0 | 11 | 76 | 100% |
| Qwen3 Coder Next | Mid | 3 | 0 | 5 | 412 | 100% |
| Claude Opus 4.6 | Frontier | 0 | 3 | 1 | 326 | 0% |
| DeepSeek V4 Flash | Mid | 1 | 1 | 4 | 82 | 50% |
| GLM 5 Turbo | Frontier | 0 | 2 | 65 | 263 | 0% |
| Devstral 2 2512 | Mid | 1 | 0 | 0 | 402 | 100% |
| GPT 5.4 | Frontier | 1 | 0 | 0 | 326 | 100% |
| Claude Haiku 4.5 | Small | 0 | 0 | 5 | 401 | n/a |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 89 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 1 | 89 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 0 | 419 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 25 | 393 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 3 | 87 | n/a |
| Prompt | Tier | Amplitude | Tinybird | None | Other | A rate |
|---|---|---|---|---|---|---|
| url-shortener | Intermediate | 2 | 73 | 75 | 385 | 3% |
| url-shortener | Beginner | 0 | 70 | 109 | 357 | 0% |
| fitness-tracking-app | Advanced | 42 | 5 | 13 | 466 | 89% |
| ai-revenue-ops-copilot | Intermediate | 36 | 0 | 3 | 490 | 100% |
| ai-revenue-ops-copilot | Advanced | 31 | 1 | 16 | 458 | 97% |
| url-shortener | Advanced | 2 | 28 | 5 | 497 | 7% |
| fitness-tracking-app | Beginner | 17 | 0 | 1 | 518 | 100% |
| fitness-tracking-app | Intermediate | 13 | 0 | 16 | 508 | 100% |
| saas-application | Advanced | 8 | 2 | 30 | 496 | 80% |
| multi-tenant-crm | Advanced | 0 | 10 | 37 | 489 | 0% |
| saas-application | Intermediate | 2 | 2 | 52 | 479 | 50% |
| ai-revenue-ops-copilot | Beginner | 1 | 0 | 5 | 514 | 100% |
| multi-tenant-crm | Beginner | 1 | 0 | 47 | 486 | 100% |
| multi-tenant-crm | Intermediate | 0 | 1 | 34 | 495 | 0% |
| saas-application | Beginner | 0 | 0 | 16 | 521 | n/a |