Leading: OpenWeatherMap (71.1%)
| Metric | Value |
|---|---|
| FastAPI wins | 463 |
| OpenWeatherMap wins | 1138 |
| Abstains (no tool) | 896 |
| Other tool chosen | 4082 |
| Decisive cases | 1601 |
| FastAPI win rate (unweighted) | 28.9% |
| 95% CI | 26.8% - 31.2% |
| FastAPI win rate (weighted) | 28.9% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | FastAPI | OpenWeatherMap | None | Other | A rate |
|---|---|---|---|---|---|---|
| Mistral Small 4 | Mid | 39 | 83 | 12 | 188 | 32% |
| Qwen3 Coder Next | Mid | 36 | 79 | 113 | 107 | 31% |
| DeepSeek R1 0528 | Frontier | 61 | 47 | 84 | 162 | 56% |
| Gemini 2.5 Pro | Frontier | 40 | 46 | 30 | 239 | 47% |
| Llama 4 Maverick | Frontier | 0 | 84 | 17 | 243 | 0% |
| GPT 5.4 | Frontier | 49 | 31 | 22 | 144 | 61% |
| GPT 5.3 Codex | Frontier | 40 | 37 | 17 | 261 | 52% |
| Devstral 2 2512 | Mid | 24 | 53 | 49 | 192 | 31% |
| Claude Opus 4.6 | Frontier | 21 | 50 | 13 | 167 | 30% |
| MiMo V2 Pro | Frontier | 10 | 61 | 24 | 156 | 14% |
| Claude Haiku 4.5 | Small | 30 | 40 | 18 | 243 | 43% |
| Llama 4 Scout | Small | 2 | 68 | 30 | 222 | 3% |
| MiniMax M2.7 | Frontier | 31 | 33 | 25 | 146 | 48% |
| Gemini 2.5 Flash | Small | 0 | 63 | 36 | 147 | 0% |
| GLM 5 Turbo | Frontier | 6 | 54 | 142 | 49 | 10% |
| GPT 5.4 Mini | Mid | 2 | 54 | 17 | 236 | 4% |
| DeepSeek V3.2 | Mid | 25 | 26 | 26 | 169 | 49% |
| Claude Sonnet 4.6 | Frontier | 2 | 48 | 14 | 289 | 4% |
| Kimi K2.5 | Frontier | 3 | 30 | 35 | 172 | 9% |
| DeepSeek V4 Flash | Mid | 9 | 21 | 14 | 51 | 30% |
| MiMo V2.5 Pro | Frontier | 8 | 19 | 11 | 65 | 30% |
| GLM 5.2 | Frontier | 8 | 17 | 11 | 68 | 32% |
| Kimi K2.7 Code | Frontier | 8 | 15 | 10 | 71 | 35% |
| DeepSeek V4 Pro | Frontier | 3 | 20 | 32 | 45 | 13% |
| Claude Opus 4.8 | Frontier | 1 | 18 | 36 | 48 | 5% |
| MiniMax M3 | Frontier | 1 | 18 | 13 | 70 | 5% |
| GPT 5.5 | Frontier | 1 | 13 | 10 | 79 | 7% |
| Gemini 3.5 Flash | Small | 3 | 10 | 35 | 53 | 23% |
| Prompt | Tier | FastAPI | OpenWeatherMap | None | Other | A rate |
|---|---|---|---|---|---|---|
| weather-dashboard | Intermediate | 0 | 450 | 1 | 82 | 0% |
| weather-dashboard | Beginner | 0 | 435 | 0 | 101 | 0% |
| weather-dashboard | Advanced | 14 | 253 | 6 | 242 | 5% |
| ai-revenue-ops-copilot | Advanced | 120 | 0 | 90 | 298 | 100% |
| url-shortener | Advanced | 110 | 0 | 43 | 368 | 100% |
| url-shortener | Intermediate | 64 | 0 | 93 | 365 | 100% |
| ai-revenue-ops-copilot | Beginner | 58 | 0 | 26 | 410 | 100% |
| ai-revenue-ops-copilot | Intermediate | 57 | 0 | 97 | 353 | 100% |
| multi-tenant-crm | Intermediate | 17 | 0 | 112 | 387 | 100% |
| url-shortener | Beginner | 14 | 0 | 125 | 383 | 100% |
| multi-tenant-crm | Advanced | 6 | 0 | 35 | 488 | 100% |
| full-stack-web-app | Advanced | 2 | 0 | 11 | 95 | 100% |
| multi-tenant-crm | Beginner | 1 | 0 | 148 | 376 | 100% |
| full-stack-web-app | Beginner | 0 | 0 | 74 | 61 | n/a |
| full-stack-web-app | Intermediate | 0 | 0 | 35 | 73 | n/a |