| Metric | Value |
|---|---|
| OneSignal wins | 1336 |
| Firebase wins | 1416 |
| Abstains (no tool) | 112 |
| Other tool chosen | 3484 |
| Decisive cases | 2752 |
| OneSignal win rate (unweighted) | 48.5% |
| 95% CI | 46.7% - 50.4% |
| OneSignal win rate (weighted) | 48.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | OneSignal | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 239 | 8 | 1 | 87 | 97% |
| Mistral Small 4 | Mid | 10 | 212 | 0 | 107 | 5% |
| Devstral 2 2512 | Mid | 12 | 203 | 0 | 118 | 6% |
| Qwen3 Coder Next | Mid | 78 | 123 | 1 | 133 | 39% |
| DeepSeek R1 0528 | Frontier | 59 | 136 | 26 | 112 | 30% |
| MiMo V2 Pro | Frontier | 77 | 102 | 4 | 141 | 43% |
| Claude Opus 4.6 | Frontier | 64 | 89 | 0 | 171 | 42% |
| MiniMax M2.7 | Frontier | 9 | 140 | 17 | 151 | 6% |
| GPT 5.4 | Frontier | 113 | 32 | 0 | 179 | 78% |
| GPT 5.3 Codex | Frontier | 129 | 11 | 0 | 196 | 92% |
| Claude Sonnet 4.6 | Frontier | 66 | 56 | 0 | 214 | 54% |
| Llama 4 Scout | Small | 75 | 44 | 4 | 208 | 63% |
| DeepSeek V3.2 | Mid | 97 | 18 | 16 | 191 | 84% |
| Gemini 2.5 Flash | Small | 40 | 73 | 10 | 199 | 35% |
| GPT 5.4 Mini | Mid | 67 | 40 | 6 | 221 | 63% |
| Claude Haiku 4.5 | Small | 0 | 105 | 0 | 222 | 0% |
| Gemini 2.5 Pro | Frontier | 69 | 4 | 2 | 257 | 95% |
| Kimi K2.5 | Frontier | 61 | 2 | 8 | 251 | 97% |
| GLM 5 Turbo | Frontier | 42 | 7 | 17 | 258 | 86% |
| DeepSeek V4 Pro | Frontier | 3 | 3 | 0 | 6 | 50% |
| MiMo V2.5 Pro | Frontier | 2 | 4 | 0 | 6 | 33% |
| GLM 5.2 | Frontier | 5 | 0 | 0 | 7 | 100% |
| DeepSeek V4 Flash | Mid | 4 | 1 | 0 | 7 | 80% |
| Claude Opus 4.8 | Frontier | 3 | 2 | 0 | 7 | 60% |
| MiniMax M3 | Frontier | 4 | 0 | 0 | 8 | 100% |
| GPT 5.5 | Frontier | 3 | 1 | 0 | 8 | 75% |
| Kimi K2.7 Code | Frontier | 3 | 0 | 0 | 9 | 100% |
| Gemini 3.5 Flash | Small | 2 | 0 | 0 | 10 | 100% |
| Prompt | Tier | OneSignal | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| chat-application | Intermediate | 142 | 265 | 3 | 27 | 35% |
| chat-application | Beginner | 185 | 204 | 14 | 30 | 48% |
| social-media-platform | Beginner | 210 | 127 | 6 | 95 | 62% |
| chat-application | Advanced | 144 | 184 | 6 | 101 | 44% |
| social-media-platform | Intermediate | 206 | 98 | 0 | 131 | 68% |
| social-media-platform | Advanced | 101 | 63 | 3 | 268 | 62% |
| project-management-tool | Intermediate | 44 | 91 | 13 | 280 | 33% |
| project-management-tool | Beginner | 48 | 74 | 21 | 294 | 39% |
| chat-application | Intermediate | 28 | 64 | 0 | 3 | 30% |
| chat-application | Beginner | 35 | 45 | 1 | 14 | 44% |
| social-media-platform | Beginner | 41 | 33 | 1 | 20 | 55% |
| chat-application | Advanced | 35 | 39 | 2 | 19 | 47% |
| project-management-tool | Advanced | 34 | 26 | 4 | 363 | 57% |
| social-media-platform | Intermediate | 32 | 26 | 0 | 36 | 55% |
| social-media-platform | Advanced | 19 | 17 | 0 | 59 | 53% |
| project-management-tool | Intermediate | 10 | 20 | 4 | 61 | 33% |
| restaurant-reservation-system | Advanced | 7 | 15 | 17 | 395 | 32% |
| project-management-tool | Beginner | 6 | 13 | 7 | 68 | 32% |
| restaurant-reservation-system | Beginner | 2 | 4 | 3 | 427 | 33% |
| restaurant-reservation-system | Advanced | 0 | 5 | 2 | 87 | 0% |
| project-management-tool | Advanced | 4 | 0 | 1 | 88 | 100% |
| restaurant-reservation-system | Intermediate | 2 | 1 | 2 | 433 | 67% |
| restaurant-reservation-system | Intermediate | 1 | 1 | 1 | 92 | 50% |
| restaurant-reservation-system | Beginner | 0 | 1 | 1 | 93 | 0% |