| Metric | Value |
|---|---|
| OneSignal wins | 1024 |
| Firebase wins | 1043 |
| Abstains (no tool) | 89 |
| Other tool chosen | 2592 |
| Decisive cases | 2067 |
| OneSignal win rate (unweighted) | 49.5% |
| 95% CI | 47.4% - 51.7% |
| OneSignal win rate (weighted) | 49.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | OneSignal | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 182 | 7 | 1 | 62 | 96% |
| Mistral Small 4 | Mid | 7 | 155 | 0 | 85 | 4% |
| Devstral 2 2512 | Mid | 10 | 151 | 0 | 88 | 6% |
| Qwen3 Coder Next | Mid | 60 | 90 | 0 | 102 | 40% |
| DeepSeek R1 0528 | Frontier | 44 | 106 | 19 | 81 | 29% |
| MiMo V2 Pro | Frontier | 60 | 77 | 4 | 111 | 44% |
| Claude Opus 4.6 | Frontier | 57 | 65 | 0 | 130 | 47% |
| MiniMax M2.7 | Frontier | 6 | 108 | 13 | 119 | 5% |
| GPT 5.4 | Frontier | 93 | 20 | 0 | 139 | 82% |
| GPT 5.3 Codex | Frontier | 101 | 5 | 0 | 146 | 95% |
| DeepSeek V3.2 | Mid | 80 | 17 | 12 | 141 | 82% |
| Claude Sonnet 4.6 | Frontier | 52 | 43 | 0 | 157 | 55% |
| Llama 4 Scout | Small | 56 | 36 | 3 | 152 | 61% |
| Gemini 2.5 Flash | Small | 35 | 51 | 8 | 157 | 41% |
| GPT 5.4 Mini | Mid | 51 | 27 | 6 | 166 | 65% |
| Claude Haiku 4.5 | Small | 0 | 75 | 0 | 169 | 0% |
| Gemini 2.5 Pro | Frontier | 54 | 3 | 2 | 189 | 95% |
| Kimi K2.5 | Frontier | 45 | 1 | 7 | 197 | 98% |
| GLM 5 Turbo | Frontier | 31 | 6 | 14 | 201 | 84% |
| Prompt | Tier | OneSignal | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| chat-application | Intermediate | 129 | 242 | 3 | 24 | 35% |
| chat-application | Beginner | 165 | 186 | 13 | 30 | 47% |
| social-media-platform | Beginner | 194 | 114 | 6 | 85 | 63% |
| chat-application | Advanced | 125 | 169 | 6 | 96 | 43% |
| social-media-platform | Intermediate | 190 | 90 | 0 | 117 | 68% |
| social-media-platform | Advanced | 95 | 57 | 3 | 241 | 63% |
| project-management-tool | Intermediate | 42 | 80 | 13 | 254 | 34% |
| project-management-tool | Beginner | 43 | 66 | 20 | 269 | 39% |
| project-management-tool | Advanced | 31 | 23 | 4 | 332 | 57% |
| restaurant-reservation-system | Advanced | 6 | 13 | 16 | 360 | 32% |
| restaurant-reservation-system | Beginner | 2 | 3 | 3 | 389 | 40% |
| restaurant-reservation-system | Intermediate | 2 | 0 | 2 | 395 | 100% |
