Leading: OpenWeatherMap (71.1%)
| Metric | Value |
|---|---|
| OpenWeatherMap wins | 1138 |
| FastAPI wins | 463 |
| Abstains (no tool) | 896 |
| Other tool chosen | 4082 |
| Decisive cases | 1601 |
| OpenWeatherMap win rate (unweighted) | 71.1% |
| 95% CI | 68.8% - 73.2% |
| OpenWeatherMap win rate (weighted) | 71.1% |
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 | 39 | 12 | 188 | 68% |
| Qwen3 Coder Next | Mid | 79 | 36 | 113 | 107 | 69% |
| DeepSeek R1 0528 | Frontier | 47 | 61 | 84 | 162 | 44% |
| Gemini 2.5 Pro | Frontier | 46 | 40 | 30 | 239 | 53% |
| Llama 4 Maverick | Frontier | 84 | 0 | 17 | 243 | 100% |
| GPT 5.4 | Frontier | 31 | 49 | 22 | 144 | 39% |
| Devstral 2 2512 | Mid | 53 | 24 | 49 | 192 | 69% |
| GPT 5.3 Codex | Frontier | 37 | 40 | 17 | 261 | 48% |
| MiMo V2 Pro | Frontier | 61 | 10 | 24 | 156 | 86% |
| Claude Opus 4.6 | Frontier | 50 | 21 | 13 | 167 | 70% |
| Llama 4 Scout | Small | 68 | 2 | 30 | 222 | 97% |
| Claude Haiku 4.5 | Small | 40 | 30 | 18 | 243 | 57% |
| MiniMax M2.7 | Frontier | 33 | 31 | 25 | 146 | 52% |
| Gemini 2.5 Flash | Small | 63 | 0 | 36 | 147 | 100% |
| GLM 5 Turbo | Frontier | 54 | 6 | 142 | 49 | 90% |
| GPT 5.4 Mini | Mid | 54 | 2 | 17 | 236 | 96% |
| DeepSeek V3.2 | Mid | 26 | 25 | 26 | 169 | 51% |
| Claude Sonnet 4.6 | Frontier | 48 | 2 | 14 | 289 | 96% |
| Kimi K2.5 | Frontier | 30 | 3 | 35 | 172 | 91% |
| DeepSeek V4 Flash | Mid | 21 | 9 | 14 | 51 | 70% |
| MiMo V2.5 Pro | Frontier | 19 | 8 | 11 | 65 | 70% |
| GLM 5.2 | Frontier | 17 | 8 | 11 | 68 | 68% |
| DeepSeek V4 Pro | Frontier | 20 | 3 | 32 | 45 | 87% |
| Kimi K2.7 Code | Frontier | 15 | 8 | 10 | 71 | 65% |
| Claude Opus 4.8 | Frontier | 18 | 1 | 36 | 48 | 95% |
| MiniMax M3 | Frontier | 18 | 1 | 13 | 70 | 95% |
| GPT 5.5 | Frontier | 13 | 1 | 10 | 79 | 93% |
| Gemini 3.5 Flash | Small | 10 | 3 | 35 | 53 | 77% |
| Prompt | Tier | OpenWeatherMap | FastAPI | None | Other | A rate |
|---|---|---|---|---|---|---|
| weather-dashboard | Intermediate | 450 | 0 | 1 | 82 | 100% |
| weather-dashboard | Beginner | 435 | 0 | 0 | 101 | 100% |
| weather-dashboard | Advanced | 253 | 14 | 6 | 242 | 95% |
| ai-revenue-ops-copilot | Advanced | 0 | 120 | 90 | 298 | 0% |
| url-shortener | Advanced | 0 | 110 | 43 | 368 | 0% |
| url-shortener | Intermediate | 0 | 64 | 93 | 365 | 0% |
| ai-revenue-ops-copilot | Beginner | 0 | 58 | 26 | 410 | 0% |
| ai-revenue-ops-copilot | Intermediate | 0 | 57 | 97 | 353 | 0% |
| multi-tenant-crm | Intermediate | 0 | 17 | 112 | 387 | 0% |
| url-shortener | Beginner | 0 | 14 | 125 | 383 | 0% |
| multi-tenant-crm | Advanced | 0 | 6 | 35 | 488 | 0% |
| full-stack-web-app | Advanced | 0 | 2 | 11 | 95 | 0% |
| multi-tenant-crm | Beginner | 0 | 1 | 148 | 376 | 0% |
| full-stack-web-app | Beginner | 0 | 0 | 74 | 61 | n/a |
| full-stack-web-app | Intermediate | 0 | 0 | 35 | 73 | n/a |