Leading: OpenWeatherMap (70.9%)
| Metric | Value |
|---|---|
| OpenWeatherMap wins | 1129 |
| FastAPI wins | 464 |
| Abstains (no tool) | 879 |
| Other tool chosen | 3954 |
| Decisive cases | 1593 |
| OpenWeatherMap win rate (unweighted) | 70.9% |
| 95% CI | 68.6% - 73.1% |
| OpenWeatherMap win rate (weighted) | 70.9% |
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 | 40 | 9 | 181 | 68% |
| Qwen3 Coder Next | Mid | 78 | 36 | 110 | 103 | 68% |
| DeepSeek R1 0528 | Frontier | 46 | 59 | 81 | 161 | 44% |
| Gemini 2.5 Pro | Frontier | 47 | 38 | 31 | 230 | 55% |
| GPT 5.4 | Frontier | 34 | 51 | 26 | 156 | 40% |
| Llama 4 Maverick | Frontier | 83 | 0 | 15 | 241 | 100% |
| Devstral 2 2512 | Mid | 57 | 26 | 54 | 201 | 69% |
| MiMo V2 Pro | Frontier | 65 | 13 | 30 | 164 | 83% |
| Claude Opus 4.6 | Frontier | 53 | 24 | 14 | 181 | 69% |
| GPT 5.3 Codex | Frontier | 36 | 38 | 16 | 256 | 49% |
| Llama 4 Scout | Small | 70 | 2 | 25 | 220 | 97% |
| Gemini 2.5 Flash | Small | 69 | 2 | 40 | 155 | 97% |
| Claude Haiku 4.5 | Small | 39 | 29 | 23 | 233 | 57% |
| MiniMax M2.7 | Frontier | 34 | 32 | 30 | 159 | 52% |
| GLM 5 Turbo | Frontier | 59 | 6 | 152 | 55 | 91% |
| GPT 5.4 Mini | Mid | 55 | 3 | 17 | 228 | 95% |
| DeepSeek V3.2 | Mid | 31 | 27 | 30 | 178 | 53% |
| Claude Sonnet 4.6 | Frontier | 49 | 2 | 12 | 281 | 96% |
| Kimi K2.5 | Frontier | 32 | 3 | 38 | 183 | 91% |
| DeepSeek V4 Flash | Mid | 15 | 8 | 12 | 33 | 65% |
| MiMo V2.5 Pro | Frontier | 13 | 6 | 7 | 48 | 68% |
| DeepSeek V4 Pro | Frontier | 15 | 3 | 23 | 31 | 83% |
| GLM 5.2 | Frontier | 11 | 6 | 8 | 50 | 65% |
| Kimi K2.7 Code | Frontier | 11 | 5 | 9 | 49 | 69% |
| MiniMax M3 | Frontier | 14 | 1 | 10 | 48 | 93% |
| Claude Opus 4.8 | Frontier | 12 | 0 | 24 | 37 | 100% |
| Gemini 3.5 Flash | Small | 8 | 3 | 26 | 35 | 73% |
| GPT 5.5 | Frontier | 9 | 1 | 7 | 57 | 90% |
| Prompt | Tier | OpenWeatherMap | FastAPI | None | Other | A rate |
|---|---|---|---|---|---|---|
| weather-dashboard | Intermediate | 432 | 0 | 1 | 81 | 100% |
| weather-dashboard | Beginner | 418 | 0 | 0 | 99 | 100% |
| weather-dashboard | Advanced | 239 | 14 | 5 | 240 | 94% |
| ai-revenue-ops-copilot | Advanced | 0 | 117 | 88 | 284 | 0% |
| url-shortener | Advanced | 0 | 112 | 44 | 349 | 0% |
| url-shortener | Intermediate | 0 | 61 | 91 | 349 | 0% |
| ai-revenue-ops-copilot | Intermediate | 0 | 56 | 95 | 337 | 0% |
| ai-revenue-ops-copilot | Beginner | 0 | 54 | 27 | 392 | 0% |
| weather-dashboard | Beginner | 18 | 0 | 0 | 1 | 100% |
| multi-tenant-crm | Intermediate | 0 | 15 | 109 | 371 | 0% |
| url-shortener | Beginner | 0 | 14 | 120 | 372 | 0% |
| weather-dashboard | Intermediate | 13 | 0 | 1 | 5 | 100% |
| weather-dashboard | Advanced | 9 | 1 | 0 | 8 | 90% |
| multi-tenant-crm | Advanced | 0 | 6 | 36 | 471 | 0% |
| url-shortener | Advanced | 0 | 6 | 3 | 10 | 0% |
| url-shortener | Intermediate | 0 | 4 | 5 | 10 | 0% |
| full-stack-web-app | Advanced | 0 | 2 | 7 | 67 | 0% |
| multi-tenant-crm | Beginner | 0 | 1 | 138 | 366 | 0% |
| url-shortener | Beginner | 0 | 1 | 12 | 6 | 0% |
| full-stack-web-app | Beginner | 0 | 0 | 51 | 47 | n/a |
| full-stack-web-app | Intermediate | 0 | 0 | 23 | 57 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 13 | 5 | n/a |
| multi-tenant-crm | Advanced | 0 | 0 | 3 | 16 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 7 | 11 | n/a |