| Metric | Value |
|---|---|
| Twilio wins | 1122 |
| Firebase wins | 1099 |
| Abstains (no tool) | 92 |
| Other tool chosen | 2662 |
| Decisive cases | 2221 |
| Twilio win rate (unweighted) | 50.5% |
| 95% CI | 48.4% - 52.6% |
| Twilio win rate (weighted) | 50.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Twilio | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 49 | 158 | 0 | 54 | 24% |
| Mistral Small 4 | Mid | 37 | 165 | 0 | 57 | 18% |
| MiniMax M2.7 | Frontier | 57 | 111 | 14 | 76 | 34% |
| DeepSeek R1 0528 | Frontier | 49 | 110 | 20 | 83 | 31% |
| Qwen3 Coder Next | Mid | 63 | 94 | 0 | 106 | 40% |
| MiMo V2 Pro | Frontier | 68 | 83 | 4 | 109 | 45% |
| Claude Haiku 4.5 | Small | 63 | 82 | 0 | 111 | 43% |
| Claude Opus 4.6 | Frontier | 66 | 68 | 0 | 130 | 49% |
| Gemini 2.5 Flash | Small | 65 | 55 | 8 | 135 | 54% |
| GPT 5.4 Mini | Mid | 77 | 29 | 6 | 150 | 73% |
| Llama 4 Scout | Small | 68 | 38 | 3 | 150 | 64% |
| GPT 5.4 | Frontier | 73 | 22 | 0 | 169 | 77% |
| Claude Sonnet 4.6 | Frontier | 47 | 45 | 0 | 172 | 51% |
| GLM 5 Turbo | Frontier | 66 | 6 | 15 | 177 | 92% |
| GPT 5.3 Codex | Frontier | 66 | 5 | 0 | 193 | 93% |
| Llama 4 Maverick | Frontier | 59 | 7 | 1 | 197 | 89% |
| DeepSeek V3.2 | Mid | 42 | 17 | 12 | 191 | 71% |
| Kimi K2.5 | Frontier | 56 | 1 | 7 | 198 | 98% |
| Gemini 2.5 Pro | Frontier | 51 | 3 | 2 | 204 | 94% |
| Prompt | Tier | Twilio | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| restaurant-reservation-system | Beginner | 397 | 4 | 3 | 12 | 99% |
| restaurant-reservation-system | Intermediate | 387 | 0 | 2 | 29 | 100% |
| restaurant-reservation-system | Advanced | 309 | 14 | 17 | 74 | 96% |
| chat-application | Intermediate | 0 | 254 | 3 | 160 | 0% |
| chat-application | Beginner | 2 | 196 | 14 | 201 | 1% |
| chat-application | Advanced | 10 | 176 | 6 | 223 | 5% |
| social-media-platform | Beginner | 1 | 119 | 6 | 292 | 1% |
| social-media-platform | Intermediate | 5 | 95 | 0 | 316 | 5% |
| project-management-tool | Intermediate | 1 | 87 | 13 | 307 | 1% |
| project-management-tool | Beginner | 2 | 70 | 21 | 324 | 3% |
| social-media-platform | Advanced | 7 | 60 | 3 | 345 | 10% |
| project-management-tool | Advanced | 1 | 24 | 4 | 379 | 4% |
