| Metric | Value |
|---|---|
| Twilio wins | 444 |
| Firebase wins | 459 |
| Abstains (no tool) | 39 |
| Other tool chosen | 1094 |
| Decisive cases | 903 |
| Twilio win rate (unweighted) | 49.2% |
| 95% CI | 45.9% - 52.4% |
| Twilio win rate (weighted) | 49.2% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Twilio | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 19 | 66 | 0 | 22 | 22% |
| Mistral Small 4 | Mid | 13 | 64 | 0 | 31 | 17% |
| DeepSeek R1 0528 | Frontier | 19 | 51 | 9 | 27 | 27% |
| MiniMax M2.7 | Frontier | 23 | 46 | 7 | 30 | 33% |
| Qwen3 Coder Next | Mid | 27 | 40 | 0 | 41 | 40% |
| MiMo V2 Pro | Frontier | 27 | 36 | 2 | 43 | 43% |
| Claude Haiku 4.5 | Small | 24 | 34 | 0 | 44 | 41% |
| Claude Opus 4.6 | Frontier | 27 | 29 | 0 | 52 | 48% |
| Gemini 2.5 Flash | Small | 26 | 24 | 3 | 55 | 52% |
| GPT 5.4 Mini | Mid | 32 | 10 | 2 | 64 | 76% |
| GPT 5.4 | Frontier | 29 | 12 | 0 | 67 | 71% |
| Llama 4 Scout | Small | 27 | 14 | 2 | 64 | 66% |
| Claude Sonnet 4.6 | Frontier | 19 | 18 | 0 | 71 | 51% |
| GLM 5 Turbo | Frontier | 27 | 3 | 5 | 73 | 90% |
| GPT 5.3 Codex | Frontier | 27 | 2 | 0 | 79 | 93% |
| Llama 4 Maverick | Frontier | 23 | 3 | 1 | 81 | 88% |
| Kimi K2.5 | Frontier | 21 | 0 | 3 | 83 | 100% |
| DeepSeek V3.2 | Mid | 16 | 5 | 4 | 81 | 76% |
| Gemini 2.5 Pro | Frontier | 18 | 2 | 1 | 86 | 90% |
| Prompt | Tier | Twilio | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| restaurant-reservation-system | Beginner | 162 | 1 | 2 | 5 | 99% |
| restaurant-reservation-system | Intermediate | 155 | 0 | 2 | 14 | 100% |
| restaurant-reservation-system | Advanced | 115 | 7 | 8 | 39 | 94% |
| chat-application | Intermediate | 0 | 104 | 0 | 67 | 0% |
| chat-application | Advanced | 3 | 77 | 4 | 87 | 4% |
| chat-application | Beginner | 2 | 75 | 6 | 84 | 3% |
| social-media-platform | Beginner | 0 | 52 | 2 | 117 | 0% |
| social-media-platform | Intermediate | 4 | 42 | 0 | 125 | 9% |
| project-management-tool | Intermediate | 0 | 37 | 5 | 126 | 0% |
| project-management-tool | Beginner | 0 | 30 | 7 | 133 | 0% |
| social-media-platform | Advanced | 2 | 25 | 1 | 143 | 7% |
| project-management-tool | Advanced | 1 | 9 | 2 | 154 | 10% |
