| Metric | Value |
|---|---|
| Firebase wins | 1381 |
| OneSignal wins | 1406 |
| Abstains (no tool) | 94 |
| Other tool chosen | 3506 |
| Decisive cases | 2787 |
| Firebase win rate (unweighted) | 49.6% |
| 95% CI | 47.7% - 51.4% |
| Firebase win rate (weighted) | 49.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Firebase | OneSignal | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 7 | 244 | 1 | 83 | 3% |
| Mistral Small 4 | Mid | 207 | 10 | 1 | 109 | 95% |
| DeepSeek R1 0528 | Frontier | 142 | 61 | 22 | 109 | 70% |
| Qwen3 Coder Next | Mid | 125 | 78 | 0 | 132 | 62% |
| Devstral 2 2512 | Mid | 192 | 9 | 0 | 109 | 96% |
| GPT 5.3 Codex | Frontier | 10 | 131 | 0 | 194 | 7% |
| MiMo V2 Pro | Frontier | 79 | 57 | 4 | 112 | 58% |
| Llama 4 Scout | Small | 56 | 72 | 3 | 200 | 44% |
| Claude Opus 4.6 | Frontier | 65 | 56 | 0 | 131 | 54% |
| Claude Sonnet 4.6 | Frontier | 54 | 65 | 0 | 217 | 45% |
| MiniMax M2.7 | Frontier | 108 | 7 | 12 | 119 | 94% |
| GPT 5.4 | Frontier | 21 | 94 | 0 | 137 | 18% |
| Claude Haiku 4.5 | Small | 103 | 0 | 0 | 220 | 100% |
| GPT 5.4 Mini | Mid | 42 | 59 | 8 | 224 | 42% |
| DeepSeek V3.2 | Mid | 17 | 79 | 12 | 142 | 18% |
| Gemini 2.5 Flash | Small | 53 | 34 | 8 | 156 | 61% |
| Gemini 2.5 Pro | Frontier | 3 | 76 | 2 | 251 | 4% |
| MiMo V2.5 Pro | Frontier | 26 | 20 | 2 | 35 | 57% |
| Kimi K2.5 | Frontier | 1 | 45 | 5 | 199 | 2% |
| DeepSeek V4 Flash | Mid | 7 | 36 | 0 | 39 | 16% |
| GLM 5 Turbo | Frontier | 6 | 31 | 14 | 201 | 16% |
| DeepSeek V4 Pro | Frontier | 19 | 17 | 0 | 48 | 53% |
| GLM 5.2 | Frontier | 1 | 33 | 0 | 50 | 3% |
| Claude Opus 4.8 | Frontier | 19 | 12 | 0 | 51 | 61% |
| GPT 5.5 | Frontier | 12 | 18 | 0 | 54 | 40% |
| Kimi K2.7 Code | Frontier | 6 | 22 | 0 | 56 | 21% |
| MiniMax M3 | Frontier | 0 | 24 | 0 | 60 | 0% |
| Gemini 3.5 Flash | Small | 0 | 16 | 0 | 68 | 0% |
| Prompt | Tier | Firebase | OneSignal | None | Other | A rate |
|---|---|---|---|---|---|---|
| chat-application | Intermediate | 324 | 176 | 3 | 31 | 65% |
| chat-application | Beginner | 244 | 241 | 13 | 34 | 50% |
| social-media-platform | Beginner | 151 | 272 | 6 | 108 | 36% |
| chat-application | Advanced | 221 | 186 | 6 | 121 | 54% |
| social-media-platform | Intermediate | 117 | 248 | 1 | 168 | 32% |
| social-media-platform | Advanced | 75 | 126 | 4 | 329 | 37% |
| project-management-tool | Intermediate | 105 | 50 | 12 | 356 | 68% |
| project-management-tool | Beginner | 87 | 59 | 21 | 367 | 60% |
| project-management-tool | Advanced | 34 | 39 | 4 | 442 | 47% |
| restaurant-reservation-system | Advanced | 16 | 6 | 19 | 493 | 73% |
| restaurant-reservation-system | Beginner | 4 | 1 | 3 | 527 | 80% |
| restaurant-reservation-system | Intermediate | 3 | 2 | 2 | 530 | 60% |