| Metric | Value |
|---|---|
| Firebase wins | 1387 |
| OneSignal wins | 1404 |
| Abstains (no tool) | 101 |
| Other tool chosen | 3498 |
| Decisive cases | 2791 |
| Firebase win rate (unweighted) | 49.7% |
| 95% CI | 47.8% - 51.5% |
| Firebase win rate (weighted) | 49.7% |
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 | 245 | 1 | 82 | 3% |
| Mistral Small 4 | Mid | 208 | 10 | 1 | 109 | 95% |
| Devstral 2 2512 | Mid | 199 | 10 | 0 | 112 | 95% |
| DeepSeek R1 0528 | Frontier | 143 | 61 | 24 | 106 | 70% |
| Qwen3 Coder Next | Mid | 124 | 79 | 0 | 132 | 61% |
| MiMo V2 Pro | Frontier | 83 | 61 | 4 | 116 | 58% |
| GPT 5.3 Codex | Frontier | 9 | 131 | 0 | 196 | 6% |
| Claude Opus 4.6 | Frontier | 68 | 59 | 0 | 137 | 54% |
| Llama 4 Scout | Small | 53 | 74 | 3 | 201 | 42% |
| Claude Sonnet 4.6 | Frontier | 54 | 66 | 0 | 216 | 45% |
| GPT 5.4 | Frontier | 22 | 98 | 0 | 144 | 18% |
| MiniMax M2.7 | Frontier | 111 | 8 | 14 | 125 | 93% |
| Claude Haiku 4.5 | Small | 103 | 0 | 0 | 220 | 100% |
| GPT 5.4 Mini | Mid | 42 | 60 | 8 | 224 | 41% |
| DeepSeek V3.2 | Mid | 17 | 84 | 12 | 149 | 17% |
| Gemini 2.5 Flash | Small | 55 | 36 | 8 | 164 | 60% |
| Gemini 2.5 Pro | Frontier | 3 | 75 | 2 | 252 | 4% |
| Kimi K2.5 | Frontier | 1 | 47 | 7 | 207 | 2% |
| MiMo V2.5 Pro | Frontier | 22 | 17 | 2 | 30 | 56% |
| GLM 5 Turbo | Frontier | 6 | 33 | 15 | 210 | 15% |
| DeepSeek V4 Flash | Mid | 7 | 28 | 0 | 35 | 20% |
| DeepSeek V4 Pro | Frontier | 17 | 14 | 0 | 41 | 55% |
| GLM 5.2 | Frontier | 1 | 29 | 0 | 42 | 3% |
| Claude Opus 4.8 | Frontier | 17 | 10 | 0 | 44 | 63% |
| GPT 5.5 | Frontier | 11 | 15 | 0 | 46 | 42% |
| Kimi K2.7 Code | Frontier | 4 | 20 | 0 | 48 | 17% |
| MiniMax M3 | Frontier | 0 | 20 | 0 | 52 | 0% |
| Gemini 3.5 Flash | Small | 0 | 14 | 0 | 58 | 0% |
| Prompt | Tier | Firebase | OneSignal | None | Other | A rate |
|---|---|---|---|---|---|---|
| chat-application | Intermediate | 323 | 177 | 3 | 32 | 65% |
| chat-application | Beginner | 245 | 237 | 14 | 36 | 51% |
| social-media-platform | Beginner | 152 | 270 | 6 | 109 | 36% |
| chat-application | Advanced | 222 | 184 | 6 | 122 | 55% |
| social-media-platform | Intermediate | 116 | 252 | 1 | 165 | 32% |
| social-media-platform | Advanced | 76 | 126 | 5 | 327 | 38% |
| project-management-tool | Intermediate | 110 | 50 | 13 | 351 | 69% |
| project-management-tool | Beginner | 87 | 56 | 22 | 369 | 61% |
| project-management-tool | Advanced | 32 | 41 | 4 | 444 | 44% |
| restaurant-reservation-system | Advanced | 17 | 7 | 20 | 489 | 71% |
| restaurant-reservation-system | Beginner | 4 | 2 | 4 | 525 | 67% |
| restaurant-reservation-system | Intermediate | 3 | 2 | 3 | 529 | 60% |