Leading: OpenWeatherMap (70.7%)
| Metric | Value |
|---|---|
| OpenWeatherMap wins | 1129 |
| FastAPI wins | 468 |
| Abstains (no tool) | 879 |
| Other tool chosen | 4052 |
| Decisive cases | 1597 |
| OpenWeatherMap win rate (unweighted) | 70.7% |
| 95% CI | 68.4% - 72.9% |
| OpenWeatherMap win rate (weighted) | 70.7% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | OpenWeatherMap | FastAPI | None | Other | A rate |
|---|---|---|---|---|---|---|
| Mistral Small 4 | Mid | 83 | 40 | 11 | 185 | 67% |
| Qwen3 Coder Next | Mid | 78 | 36 | 112 | 106 | 68% |
| DeepSeek R1 0528 | Frontier | 47 | 61 | 82 | 162 | 44% |
| Gemini 2.5 Pro | Frontier | 46 | 39 | 29 | 238 | 54% |
| Llama 4 Maverick | Frontier | 84 | 0 | 16 | 243 | 100% |
| GPT 5.4 | Frontier | 32 | 51 | 23 | 152 | 39% |
| Devstral 2 2512 | Mid | 54 | 25 | 51 | 199 | 68% |
| GPT 5.3 Codex | Frontier | 37 | 40 | 16 | 259 | 48% |
| MiMo V2 Pro | Frontier | 64 | 11 | 26 | 162 | 85% |
| Claude Opus 4.6 | Frontier | 52 | 23 | 13 | 175 | 69% |
| Llama 4 Scout | Small | 69 | 2 | 26 | 223 | 97% |
| Claude Haiku 4.5 | Small | 39 | 31 | 18 | 241 | 56% |
| Gemini 2.5 Flash | Small | 66 | 0 | 38 | 154 | 100% |
| MiniMax M2.7 | Frontier | 33 | 31 | 28 | 154 | 52% |
| GLM 5 Turbo | Frontier | 56 | 6 | 148 | 53 | 90% |
| GPT 5.4 Mini | Mid | 54 | 3 | 17 | 234 | 95% |
| DeepSeek V3.2 | Mid | 28 | 27 | 28 | 174 | 51% |
| Claude Sonnet 4.6 | Frontier | 48 | 2 | 13 | 287 | 96% |
| Kimi K2.5 | Frontier | 31 | 3 | 36 | 178 | 91% |
| DeepSeek V4 Flash | Mid | 18 | 8 | 13 | 43 | 69% |
| MiMo V2.5 Pro | Frontier | 16 | 7 | 9 | 57 | 70% |
| GLM 5.2 | Frontier | 14 | 8 | 9 | 59 | 64% |
| DeepSeek V4 Pro | Frontier | 18 | 3 | 26 | 38 | 86% |
| Kimi K2.7 Code | Frontier | 12 | 6 | 10 | 61 | 67% |
| MiniMax M3 | Frontier | 15 | 1 | 12 | 60 | 94% |
| Claude Opus 4.8 | Frontier | 15 | 0 | 30 | 43 | 100% |
| GPT 5.5 | Frontier | 11 | 1 | 9 | 67 | 92% |
| Gemini 3.5 Flash | Small | 9 | 3 | 30 | 45 | 75% |
| Prompt | Tier | OpenWeatherMap | FastAPI | None | Other | A rate |
|---|---|---|---|---|---|---|
| weather-dashboard | Intermediate | 449 | 0 | 1 | 83 | 100% |
| weather-dashboard | Beginner | 433 | 0 | 0 | 103 | 100% |
| weather-dashboard | Advanced | 247 | 14 | 6 | 249 | 95% |
| ai-revenue-ops-copilot | Advanced | 0 | 122 | 92 | 292 | 0% |
| url-shortener | Advanced | 0 | 114 | 44 | 363 | 0% |
| url-shortener | Intermediate | 0 | 63 | 94 | 363 | 0% |
| ai-revenue-ops-copilot | Intermediate | 0 | 58 | 96 | 353 | 0% |
| ai-revenue-ops-copilot | Beginner | 0 | 56 | 27 | 409 | 0% |
| multi-tenant-crm | Intermediate | 0 | 17 | 114 | 383 | 0% |
| url-shortener | Beginner | 0 | 15 | 125 | 385 | 0% |
| multi-tenant-crm | Advanced | 0 | 6 | 36 | 488 | 0% |
| full-stack-web-app | Advanced | 0 | 2 | 8 | 84 | 0% |
| multi-tenant-crm | Beginner | 0 | 1 | 145 | 378 | 0% |
| full-stack-web-app | Beginner | 0 | 0 | 63 | 54 | n/a |
| full-stack-web-app | Intermediate | 0 | 0 | 28 | 65 | n/a |