| Metric | Value |
|---|---|
| Open-Meteo wins | 53 |
| Firebase wins | 65 |
| Abstains (no tool) | 569 |
| Other tool chosen | 3929 |
| Decisive cases | 118 |
| Open-Meteo win rate (unweighted) | 44.9% |
| 95% CI | 36.2% - 53.9% |
| Open-Meteo win rate (weighted) | 44.9% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Open-Meteo | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 0 | 38 | 37 | 168 | 0% |
| Claude Haiku 4.5 | Small | 35 | 0 | 15 | 186 | 100% |
| Llama 4 Scout | Small | 0 | 13 | 11 | 203 | 0% |
| Gemini 2.5 Flash | Small | 0 | 12 | 35 | 200 | 0% |
| Qwen3 Coder Next | Mid | 5 | 1 | 79 | 157 | 83% |
| MiniMax M2.7 | Frontier | 5 | 0 | 27 | 202 | 100% |
| GLM 5 Turbo | Frontier | 4 | 0 | 141 | 106 | 100% |
| GPT 5.4 | Frontier | 3 | 0 | 21 | 223 | 100% |
| Gemini 2.5 Pro | Frontier | 1 | 0 | 16 | 233 | 100% |
| DeepSeek R1 0528 | Frontier | 0 | 1 | 54 | 196 | 0% |
| Claude Opus 4.6 | Frontier | 0 | 0 | 11 | 241 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 5 | 246 | n/a |
| DeepSeek V3.2 | Mid | 0 | 0 | 27 | 218 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 9 | 241 | n/a |
| GPT 5.4 Mini | Mid | 0 | 0 | 12 | 211 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 33 | 203 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 4 | 247 | n/a |
| MiMo V2 Pro | Frontier | 0 | 0 | 26 | 225 | n/a |
| Mistral Small 4 | Mid | 0 | 0 | 6 | 223 | n/a |
| Prompt | Tier | Open-Meteo | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| url-shortener | Beginner | 0 | 35 | 88 | 267 | 0% |
| url-shortener | Intermediate | 0 | 29 | 65 | 292 | 0% |
| weather-dashboard | Advanced | 26 | 0 | 4 | 354 | 100% |
| weather-dashboard | Beginner | 23 | 0 | 0 | 376 | 100% |
| weather-dashboard | Intermediate | 4 | 0 | 1 | 392 | 100% |
| url-shortener | Advanced | 0 | 1 | 36 | 354 | 0% |
| ai-revenue-ops-copilot | Intermediate | 0 | 0 | 72 | 300 | n/a |
| ai-revenue-ops-copilot | Beginner | 0 | 0 | 24 | 337 | n/a |
| ai-revenue-ops-copilot | Advanced | 0 | 0 | 68 | 306 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 107 | 280 | n/a |
| multi-tenant-crm | Advanced | 0 | 0 | 30 | 364 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 74 | 307 | n/a |
