| Metric | Value |
|---|---|
| Firebase wins | 409 |
| Twilio wins | 395 |
| Abstains (no tool) | 34 |
| Other tool chosen | 974 |
| Decisive cases | 804 |
| Firebase win rate (unweighted) | 50.9% |
| 95% CI | 47.4% - 54.3% |
| Firebase win rate (weighted) | 50.9% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Firebase | Twilio | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 59 | 17 | 0 | 19 | 78% |
| Mistral Small 4 | Mid | 56 | 11 | 0 | 29 | 84% |
| DeepSeek R1 0528 | Frontier | 45 | 16 | 9 | 24 | 74% |
| MiniMax M2.7 | Frontier | 40 | 21 | 5 | 29 | 66% |
| Qwen3 Coder Next | Mid | 36 | 24 | 0 | 36 | 60% |
| MiMo V2 Pro | Frontier | 33 | 24 | 1 | 38 | 58% |
| Claude Haiku 4.5 | Small | 30 | 21 | 0 | 40 | 59% |
| Claude Opus 4.6 | Frontier | 26 | 24 | 0 | 46 | 52% |
| Gemini 2.5 Flash | Small | 23 | 23 | 3 | 47 | 50% |
| Llama 4 Scout | Small | 13 | 24 | 1 | 58 | 35% |
| GPT 5.4 | Frontier | 10 | 26 | 0 | 60 | 28% |
| GPT 5.4 Mini | Mid | 8 | 28 | 2 | 58 | 22% |
| Claude Sonnet 4.6 | Frontier | 16 | 17 | 0 | 63 | 48% |
| GLM 5 Turbo | Frontier | 3 | 24 | 4 | 65 | 11% |
| GPT 5.3 Codex | Frontier | 2 | 24 | 0 | 70 | 8% |
| Llama 4 Maverick | Frontier | 3 | 21 | 1 | 71 | 13% |
| DeepSeek V3.2 | Mid | 4 | 15 | 4 | 72 | 21% |
| Kimi K2.5 | Frontier | 0 | 19 | 3 | 73 | 0% |
| Gemini 2.5 Pro | Frontier | 2 | 16 | 1 | 76 | 11% |
| Prompt | Tier | Firebase | Twilio | None | Other | A rate |
|---|---|---|---|---|---|---|
| restaurant-reservation-system | Beginner | 1 | 144 | 2 | 5 | 1% |
| restaurant-reservation-system | Intermediate | 0 | 138 | 1 | 13 | 0% |
| restaurant-reservation-system | Advanced | 6 | 102 | 8 | 34 | 6% |
| chat-application | Intermediate | 91 | 0 | 0 | 61 | 100% |
| chat-application | Advanced | 69 | 3 | 3 | 77 | 96% |
| chat-application | Beginner | 68 | 2 | 5 | 74 | 97% |
| social-media-platform | Beginner | 47 | 0 | 1 | 104 | 100% |
| social-media-platform | Intermediate | 38 | 3 | 0 | 111 | 93% |
| project-management-tool | Intermediate | 33 | 0 | 5 | 112 | 100% |
| project-management-tool | Beginner | 25 | 0 | 6 | 120 | 100% |
| social-media-platform | Advanced | 22 | 2 | 1 | 127 | 92% |
| project-management-tool | Advanced | 9 | 1 | 2 | 136 | 90% |
