| Metric | Value |
|---|---|
| Firebase wins | 1941 |
| OneSignal wins | 1855 |
| Abstains (no tool) | 138 |
| Other tool chosen | 4824 |
| Decisive cases | 3796 |
| Firebase win rate (unweighted) | 51.1% |
| 95% CI | 49.5% - 52.7% |
| Firebase win rate (weighted) | 51.1% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Firebase | OneSignal | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 30 | 144 | 20 | 263 | 17% |
| DeepSeek Pro 4–4 0813 | Frontier | 22 | 18 | 0 | 56 | 55% |
| DeepSeek R1 | Frontier | 194 | 78 | 33 | 153 | 71% |
| Devstral | Mid | 270 | 13 | 0 | 151 | 95% |
| Gemini Flash 2.5–3.8 | Small | 83 | 61 | 12 | 303 | 58% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 5 | 99 | 2 | 350 | 5% |
| GLM 5 Turbo–5.3 | Frontier | 10 | 84 | 17 | 349 | 11% |
| GPT 5.4–6 Astra | Frontier | 51 | 142 | 0 | 267 | 26% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 22 | 166 | 0 | 271 | 12% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 57 | 93 | 14 | 293 | 38% |
| Haiku | Small | 145 | 0 | 1 | 301 | 100% |
| Kimi 2.5–3 | Frontier | 10 | 95 | 8 | 345 | 10% |
| Llama Maverick | Frontier | 11 | 329 | 1 | 119 | 3% |
| Llama Scout | Small | 67 | 103 | 4 | 281 | 39% |
| MiMo Pro 2–2.6 | Frontier | 146 | 102 | 6 | 205 | 59% |
| MiniMax M 2.7–3 | Frontier | 159 | 37 | 18 | 240 | 81% |
| Mistral Small | Mid | 281 | 16 | 1 | 151 | 95% |
| Opus 4.6–5.5 | Frontier | 127 | 82 | 0 | 250 | 61% |
| Qwen Coder | Mid | 174 | 104 | 1 | 181 | 63% |
| Sonnet 4.6–5.5 | Frontier | 77 | 89 | 0 | 295 | 46% |
| Prompt | Tier | Firebase | OneSignal | None | Other | A rate |
|---|---|---|---|---|---|---|
| chat-application | Intermediate | 346 | 190 | 3 | 33 | 65% |
| chat-application | Beginner | 261 | 258 | 14 | 38 | 50% |
| social-media-platform | Beginner | 161 | 295 | 6 | 114 | 35% |
| chat-application | Advanced | 235 | 200 | 6 | 132 | 54% |
| social-media-platform | Intermediate | 124 | 267 | 1 | 181 | 32% |
| social-media-platform | Advanced | 81 | 135 | 5 | 352 | 38% |
| project-management-tool | Intermediate | 113 | 54 | 13 | 381 | 68% |
| chat-application | Intermediate | 116 | 48 | 0 | 6 | 71% |
| project-management-tool | Beginner | 90 | 61 | 22 | 400 | 60% |
| chat-application | Beginner | 90 | 55 | 2 | 20 | 62% |
| social-media-platform | Beginner | 62 | 70 | 3 | 36 | 47% |
| chat-application | Advanced | 64 | 50 | 3 | 35 | 56% |
| social-media-platform | Intermediate | 46 | 50 | 1 | 53 | 48% |
| project-management-tool | Advanced | 36 | 43 | 4 | 475 | 46% |
| social-media-platform | Advanced | 32 | 34 | 1 | 103 | 48% |
| project-management-tool | Intermediate | 27 | 15 | 6 | 104 | 64% |
| project-management-tool | Beginner | 20 | 11 | 11 | 109 | 65% |
| restaurant-reservation-system | Advanced | 17 | 7 | 20 | 528 | 71% |
| restaurant-reservation-system | Beginner | 5 | 2 | 4 | 563 | 71% |
| restaurant-reservation-system | Advanced | 6 | 0 | 4 | 140 | 100% |
| restaurant-reservation-system | Intermediate | 4 | 2 | 3 | 567 | 67% |
| project-management-tool | Advanced | 0 | 6 | 2 | 142 | 0% |
| restaurant-reservation-system | Intermediate | 3 | 2 | 2 | 164 | 60% |
| restaurant-reservation-system | Beginner | 2 | 0 | 2 | 148 | 100% |