| Metric | Value |
|---|---|
| Firebase wins | 1099 |
| Twilio wins | 1122 |
| Abstains (no tool) | 92 |
| Other tool chosen | 2662 |
| Decisive cases | 2221 |
| Firebase win rate (unweighted) | 49.5% |
| 95% CI | 47.4% - 51.6% |
| Firebase win rate (weighted) | 49.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Firebase | Twilio | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 158 | 49 | 0 | 54 | 76% |
| Mistral Small 4 | Mid | 165 | 37 | 0 | 57 | 82% |
| MiniMax M2.7 | Frontier | 111 | 57 | 14 | 76 | 66% |
| DeepSeek R1 0528 | Frontier | 110 | 49 | 20 | 83 | 69% |
| Qwen3 Coder Next | Mid | 94 | 63 | 0 | 106 | 60% |
| MiMo V2 Pro | Frontier | 83 | 68 | 4 | 109 | 55% |
| Claude Haiku 4.5 | Small | 82 | 63 | 0 | 111 | 57% |
| Claude Opus 4.6 | Frontier | 68 | 66 | 0 | 130 | 51% |
| Gemini 2.5 Flash | Small | 55 | 65 | 8 | 135 | 46% |
| Llama 4 Scout | Small | 38 | 68 | 3 | 150 | 36% |
| GPT 5.4 Mini | Mid | 29 | 77 | 6 | 150 | 27% |
| GPT 5.4 | Frontier | 22 | 73 | 0 | 169 | 23% |
| Claude Sonnet 4.6 | Frontier | 45 | 47 | 0 | 172 | 49% |
| GLM 5 Turbo | Frontier | 6 | 66 | 15 | 177 | 8% |
| GPT 5.3 Codex | Frontier | 5 | 66 | 0 | 193 | 7% |
| Llama 4 Maverick | Frontier | 7 | 59 | 1 | 197 | 11% |
| DeepSeek V3.2 | Mid | 17 | 42 | 12 | 191 | 29% |
| Kimi K2.5 | Frontier | 1 | 56 | 7 | 198 | 2% |
| Gemini 2.5 Pro | Frontier | 3 | 51 | 2 | 204 | 6% |
| Prompt | Tier | Firebase | Twilio | None | Other | A rate |
|---|---|---|---|---|---|---|
| restaurant-reservation-system | Beginner | 4 | 397 | 3 | 12 | 1% |
| restaurant-reservation-system | Intermediate | 0 | 387 | 2 | 29 | 0% |
| restaurant-reservation-system | Advanced | 14 | 309 | 17 | 74 | 4% |
| chat-application | Intermediate | 254 | 0 | 3 | 160 | 100% |
| chat-application | Beginner | 196 | 2 | 14 | 201 | 99% |
| chat-application | Advanced | 176 | 10 | 6 | 223 | 95% |
| social-media-platform | Beginner | 119 | 1 | 6 | 292 | 99% |
| social-media-platform | Intermediate | 95 | 5 | 0 | 316 | 95% |
| project-management-tool | Intermediate | 87 | 1 | 13 | 307 | 99% |
| project-management-tool | Beginner | 70 | 2 | 21 | 324 | 97% |
| social-media-platform | Advanced | 60 | 7 | 3 | 345 | 90% |
| project-management-tool | Advanced | 24 | 1 | 4 | 379 | 96% |
