| Metric | Value |
|---|---|
| Firebase wins | 1416 |
| Twilio wins | 1431 |
| Abstains (no tool) | 112 |
| Other tool chosen | 3389 |
| Decisive cases | 2847 |
| Firebase win rate (unweighted) | 49.7% |
| 95% CI | 47.9% - 51.6% |
| Firebase win rate (weighted) | 49.7% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Firebase | Twilio | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 203 | 60 | 0 | 70 | 77% |
| Mistral Small 4 | Mid | 212 | 43 | 0 | 74 | 83% |
| MiniMax M2.7 | Frontier | 140 | 72 | 17 | 88 | 66% |
| Qwen3 Coder Next | Mid | 123 | 82 | 1 | 129 | 60% |
| DeepSeek R1 0528 | Frontier | 136 | 64 | 26 | 107 | 68% |
| MiMo V2 Pro | Frontier | 102 | 82 | 4 | 136 | 55% |
| Claude Haiku 4.5 | Small | 105 | 76 | 0 | 146 | 58% |
| Claude Opus 4.6 | Frontier | 89 | 81 | 0 | 154 | 52% |
| Gemini 2.5 Flash | Small | 73 | 79 | 10 | 160 | 48% |
| GPT 5.4 Mini | Mid | 40 | 97 | 6 | 191 | 29% |
| Llama 4 Scout | Small | 44 | 85 | 4 | 198 | 34% |
| Claude Sonnet 4.6 | Frontier | 56 | 64 | 0 | 216 | 47% |
| GPT 5.4 | Frontier | 32 | 88 | 0 | 204 | 27% |
| GPT 5.3 Codex | Frontier | 11 | 84 | 0 | 241 | 12% |
| GLM 5 Turbo | Frontier | 7 | 81 | 17 | 219 | 8% |
| Llama 4 Maverick | Frontier | 8 | 78 | 1 | 248 | 9% |
| Gemini 2.5 Pro | Frontier | 4 | 69 | 2 | 257 | 5% |
| Kimi K2.5 | Frontier | 2 | 70 | 8 | 242 | 3% |
| DeepSeek V3.2 | Mid | 18 | 52 | 16 | 236 | 26% |
| MiMo V2.5 Pro | Frontier | 4 | 2 | 0 | 6 | 67% |
| Claude Opus 4.8 | Frontier | 2 | 3 | 0 | 7 | 40% |
| DeepSeek V4 Pro | Frontier | 3 | 1 | 0 | 8 | 75% |
| DeepSeek V4 Flash | Mid | 1 | 3 | 0 | 8 | 25% |
| GPT 5.5 | Frontier | 1 | 3 | 0 | 8 | 25% |
| Gemini 3.5 Flash | Small | 0 | 3 | 0 | 9 | 0% |
| GLM 5.2 | Frontier | 0 | 3 | 0 | 9 | 0% |
| Kimi K2.7 Code | Frontier | 0 | 3 | 0 | 9 | 0% |
| MiniMax M3 | Frontier | 0 | 3 | 0 | 9 | 0% |
| Prompt | Tier | Firebase | Twilio | None | Other | A rate |
|---|---|---|---|---|---|---|
| restaurant-reservation-system | Beginner | 4 | 417 | 3 | 12 | 1% |
| restaurant-reservation-system | Intermediate | 1 | 405 | 2 | 30 | 0% |
| restaurant-reservation-system | Advanced | 15 | 326 | 17 | 76 | 4% |
| chat-application | Intermediate | 265 | 0 | 3 | 169 | 100% |
| chat-application | Beginner | 204 | 2 | 14 | 213 | 99% |
| chat-application | Advanced | 184 | 10 | 6 | 235 | 95% |
| social-media-platform | Beginner | 127 | 1 | 6 | 304 | 99% |
| social-media-platform | Intermediate | 98 | 6 | 0 | 331 | 94% |
| project-management-tool | Intermediate | 91 | 1 | 13 | 323 | 99% |
| restaurant-reservation-system | Intermediate | 1 | 90 | 1 | 3 | 1% |
| restaurant-reservation-system | Beginner | 1 | 85 | 1 | 8 | 1% |
| restaurant-reservation-system | Advanced | 5 | 73 | 2 | 14 | 6% |
| project-management-tool | Beginner | 74 | 2 | 21 | 340 | 97% |
| social-media-platform | Advanced | 63 | 7 | 3 | 362 | 90% |
| chat-application | Intermediate | 64 | 0 | 0 | 31 | 100% |
| chat-application | Beginner | 45 | 0 | 1 | 49 | 100% |
| chat-application | Advanced | 39 | 2 | 2 | 52 | 95% |
| social-media-platform | Beginner | 33 | 1 | 1 | 60 | 97% |
| project-management-tool | Advanced | 26 | 1 | 4 | 396 | 96% |
| social-media-platform | Intermediate | 26 | 0 | 0 | 68 | 100% |
| project-management-tool | Intermediate | 20 | 0 | 4 | 71 | 100% |
| social-media-platform | Advanced | 17 | 0 | 0 | 78 | 100% |
| project-management-tool | Beginner | 13 | 1 | 7 | 73 | 93% |
| project-management-tool | Advanced | 0 | 1 | 1 | 91 | 0% |
