Leading: OpenWeatherMap (71.5%)
| Metric | Value |
|---|---|
| OpenWeatherMap wins | 1128 |
| FastAPI wins | 449 |
| Abstains (no tool) | 881 |
| Other tool chosen | 3516 |
| Decisive cases | 1577 |
| OpenWeatherMap win rate (unweighted) | 71.5% |
| 95% CI | 69.3% - 73.7% |
| OpenWeatherMap win rate (weighted) | 71.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | OpenWeatherMap | FastAPI | None | Other | A rate |
|---|---|---|---|---|---|---|
| Mistral Small 4 | Mid | 84 | 44 | 7 | 165 | 66% |
| Qwen3 Coder Next | Mid | 78 | 36 | 101 | 95 | 68% |
| DeepSeek R1 0528 | Frontier | 47 | 50 | 80 | 146 | 48% |
| GPT 5.4 | Frontier | 43 | 53 | 38 | 169 | 45% |
| MiMo V2 Pro | Frontier | 76 | 19 | 38 | 175 | 80% |
| Llama 4 Maverick | Frontier | 83 | 4 | 16 | 219 | 95% |
| Gemini 2.5 Flash | Small | 80 | 7 | 52 | 163 | 92% |
| Devstral 2 2512 | Mid | 61 | 26 | 55 | 172 | 70% |
| Claude Opus 4.6 | Frontier | 57 | 28 | 17 | 206 | 67% |
| GPT 5.3 Codex | Frontier | 38 | 41 | 22 | 221 | 48% |
| GLM 5 Turbo | Frontier | 71 | 6 | 168 | 63 | 92% |
| Gemini 2.5 Pro | Frontier | 46 | 31 | 33 | 212 | 60% |
| MiniMax M2.7 | Frontier | 41 | 33 | 40 | 176 | 55% |
| Llama 4 Scout | Small | 72 | 1 | 23 | 200 | 99% |
| DeepSeek V3.2 | Mid | 39 | 32 | 36 | 195 | 55% |
| Claude Haiku 4.5 | Small | 43 | 24 | 41 | 198 | 64% |
| GPT 5.4 Mini | Mid | 55 | 3 | 21 | 211 | 95% |
| Claude Sonnet 4.6 | Frontier | 53 | 1 | 12 | 257 | 98% |
| Kimi K2.5 | Frontier | 38 | 3 | 51 | 200 | 93% |
| DeepSeek V4 Flash | Mid | 3 | 2 | 3 | 6 | 60% |
| Kimi K2.7 Code | Frontier | 3 | 2 | 2 | 8 | 60% |
| MiMo V2.5 Pro | Frontier | 3 | 1 | 2 | 9 | 75% |
| GLM 5.2 | Frontier | 2 | 2 | 2 | 9 | 50% |
| DeepSeek V4 Pro | Frontier | 3 | 0 | 6 | 5 | 100% |
| MiniMax M3 | Frontier | 3 | 0 | 3 | 9 | 100% |
| Claude Opus 4.8 | Frontier | 2 | 0 | 6 | 7 | 100% |
| Gemini 3.5 Flash | Small | 2 | 0 | 5 | 8 | 100% |
| GPT 5.5 | Frontier | 2 | 0 | 1 | 12 | 100% |
| Prompt | Tier | OpenWeatherMap | FastAPI | None | Other | A rate |
|---|---|---|---|---|---|---|
| weather-dashboard | Intermediate | 361 | 0 | 1 | 73 | 100% |
| weather-dashboard | Beginner | 352 | 0 | 0 | 86 | 100% |
| weather-dashboard | Advanced | 199 | 13 | 4 | 205 | 94% |
| ai-revenue-ops-copilot | Advanced | 0 | 98 | 75 | 238 | 0% |
| url-shortener | Advanced | 0 | 98 | 38 | 294 | 0% |
| weather-dashboard | Beginner | 92 | 0 | 0 | 3 | 100% |
| weather-dashboard | Intermediate | 72 | 0 | 2 | 21 | 100% |
| weather-dashboard | Advanced | 52 | 3 | 2 | 37 | 95% |
| url-shortener | Intermediate | 0 | 55 | 74 | 295 | 0% |
| ai-revenue-ops-copilot | Intermediate | 0 | 46 | 82 | 282 | 0% |
| ai-revenue-ops-copilot | Beginner | 0 | 45 | 24 | 328 | 0% |
| url-shortener | Advanced | 0 | 30 | 15 | 48 | 0% |
| url-shortener | Intermediate | 0 | 17 | 33 | 44 | 0% |
| url-shortener | Beginner | 0 | 13 | 99 | 317 | 0% |
| multi-tenant-crm | Intermediate | 0 | 11 | 89 | 319 | 0% |
| url-shortener | Beginner | 0 | 7 | 66 | 22 | 0% |
| multi-tenant-crm | Intermediate | 0 | 5 | 40 | 49 | 0% |
| multi-tenant-crm | Advanced | 0 | 5 | 32 | 396 | 0% |
| multi-tenant-crm | Advanced | 0 | 2 | 9 | 84 | 0% |
| multi-tenant-crm | Beginner | 0 | 1 | 118 | 307 | 0% |
| full-stack-web-app | Advanced | 0 | 0 | 0 | 16 | n/a |
| full-stack-web-app | Beginner | 0 | 0 | 13 | 6 | n/a |
| full-stack-web-app | Intermediate | 0 | 0 | 5 | 12 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 60 | 34 | n/a |