Leading: OpenWeatherMap (70.7%)
| Metric | Value |
|---|---|
| FastAPI wins | 468 |
| OpenWeatherMap wins | 1129 |
| Abstains (no tool) | 879 |
| Other tool chosen | 4052 |
| Decisive cases | 1597 |
| FastAPI win rate (unweighted) | 29.3% |
| 95% CI | 27.1% - 31.6% |
| FastAPI win rate (weighted) | 29.3% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | FastAPI | OpenWeatherMap | None | Other | A rate |
|---|---|---|---|---|---|---|
| Mistral Small 4 | Mid | 40 | 83 | 11 | 185 | 33% |
| Qwen3 Coder Next | Mid | 36 | 78 | 112 | 106 | 32% |
| DeepSeek R1 0528 | Frontier | 61 | 47 | 82 | 162 | 56% |
| Gemini 2.5 Pro | Frontier | 39 | 46 | 29 | 238 | 46% |
| Llama 4 Maverick | Frontier | 0 | 84 | 16 | 243 | 0% |
| GPT 5.4 | Frontier | 51 | 32 | 23 | 152 | 61% |
| Devstral 2 2512 | Mid | 25 | 54 | 51 | 199 | 32% |
| GPT 5.3 Codex | Frontier | 40 | 37 | 16 | 259 | 52% |
| Claude Opus 4.6 | Frontier | 23 | 52 | 13 | 175 | 31% |
| MiMo V2 Pro | Frontier | 11 | 64 | 26 | 162 | 15% |
| Llama 4 Scout | Small | 2 | 69 | 26 | 223 | 3% |
| Claude Haiku 4.5 | Small | 31 | 39 | 18 | 241 | 44% |
| Gemini 2.5 Flash | Small | 0 | 66 | 38 | 154 | 0% |
| MiniMax M2.7 | Frontier | 31 | 33 | 28 | 154 | 48% |
| GLM 5 Turbo | Frontier | 6 | 56 | 148 | 53 | 10% |
| GPT 5.4 Mini | Mid | 3 | 54 | 17 | 234 | 5% |
| DeepSeek V3.2 | Mid | 27 | 28 | 28 | 174 | 49% |
| Claude Sonnet 4.6 | Frontier | 2 | 48 | 13 | 287 | 4% |
| Kimi K2.5 | Frontier | 3 | 31 | 36 | 178 | 9% |
| DeepSeek V4 Flash | Mid | 8 | 18 | 13 | 43 | 31% |
| MiMo V2.5 Pro | Frontier | 7 | 16 | 9 | 57 | 30% |
| GLM 5.2 | Frontier | 8 | 14 | 9 | 59 | 36% |
| DeepSeek V4 Pro | Frontier | 3 | 18 | 26 | 38 | 14% |
| Kimi K2.7 Code | Frontier | 6 | 12 | 10 | 61 | 33% |
| MiniMax M3 | Frontier | 1 | 15 | 12 | 60 | 6% |
| Claude Opus 4.8 | Frontier | 0 | 15 | 30 | 43 | 0% |
| Gemini 3.5 Flash | Small | 3 | 9 | 30 | 45 | 25% |
| GPT 5.5 | Frontier | 1 | 11 | 9 | 67 | 8% |
| Prompt | Tier | FastAPI | OpenWeatherMap | None | Other | A rate |
|---|---|---|---|---|---|---|
| weather-dashboard | Intermediate | 0 | 449 | 1 | 83 | 0% |
| weather-dashboard | Beginner | 0 | 433 | 0 | 103 | 0% |
| weather-dashboard | Advanced | 14 | 247 | 6 | 249 | 5% |
| ai-revenue-ops-copilot | Advanced | 122 | 0 | 92 | 292 | 100% |
| url-shortener | Advanced | 114 | 0 | 44 | 363 | 100% |
| url-shortener | Intermediate | 63 | 0 | 94 | 363 | 100% |
| ai-revenue-ops-copilot | Intermediate | 58 | 0 | 96 | 353 | 100% |
| ai-revenue-ops-copilot | Beginner | 56 | 0 | 27 | 409 | 100% |
| multi-tenant-crm | Intermediate | 17 | 0 | 114 | 383 | 100% |
| url-shortener | Beginner | 15 | 0 | 125 | 385 | 100% |
| multi-tenant-crm | Advanced | 6 | 0 | 36 | 488 | 100% |
| full-stack-web-app | Advanced | 2 | 0 | 8 | 84 | 100% |
| multi-tenant-crm | Beginner | 1 | 0 | 145 | 378 | 100% |
| full-stack-web-app | Intermediate | 0 | 0 | 28 | 65 | n/a |
| full-stack-web-app | Beginner | 0 | 0 | 63 | 54 | n/a |