| Metric | Value |
|---|---|
| Firebase wins | 920 |
| Ably wins | 1251 |
| Abstains (no tool) | 54 |
| Other tool chosen | 2570 |
| Decisive cases | 2171 |
| Firebase win rate (unweighted) | 42.4% |
| 95% CI | 40.3% - 44.5% |
| Firebase win rate (weighted) | 42.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Firebase | Ably | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 237 | 0 | 0 | 6 | 100% |
| Mistral Small 4 | Mid | 104 | 54 | 0 | 89 | 66% |
| Llama 4 Scout | Small | 79 | 78 | 0 | 91 | 50% |
| GPT 5.3 Codex | Frontier | 0 | 149 | 0 | 103 | 0% |
| GPT 5.4 Mini | Mid | 20 | 120 | 4 | 104 | 14% |
| Qwen3 Coder Next | Mid | 137 | 0 | 0 | 113 | 100% |
| DeepSeek R1 0528 | Frontier | 45 | 85 | 40 | 81 | 35% |
| Claude Sonnet 4.6 | Frontier | 0 | 103 | 0 | 149 | 0% |
| GPT 5.4 | Frontier | 6 | 93 | 0 | 96 | 6% |
| Gemini 2.5 Pro | Frontier | 0 | 97 | 0 | 155 | 0% |
| Llama 4 Maverick | Frontier | 0 | 89 | 0 | 160 | 0% |
| Gemini 2.5 Flash | Small | 83 | 3 | 0 | 112 | 97% |
| Claude Haiku 4.5 | Small | 84 | 0 | 0 | 161 | 100% |
| MiniMax M2.7 | Frontier | 45 | 26 | 0 | 125 | 63% |
| Kimi K2.5 | Frontier | 0 | 70 | 5 | 121 | 0% |
| GLM 5 Turbo | Frontier | 0 | 65 | 3 | 130 | 0% |
| MiMo V2 Pro | Frontier | 54 | 9 | 0 | 134 | 86% |
| Claude Opus 4.6 | Frontier | 0 | 49 | 0 | 148 | 0% |
| GPT 5.5 | Frontier | 0 | 34 | 0 | 20 | 0% |
| MiMo V2.5 Pro | Frontier | 15 | 8 | 0 | 31 | 65% |
| DeepSeek V4 Pro | Frontier | 6 | 17 | 1 | 29 | 26% |
| GLM 5.2 | Frontier | 0 | 22 | 0 | 32 | 0% |
| Kimi K2.7 Code | Frontier | 0 | 21 | 0 | 33 | 0% |
| DeepSeek V3.2 | Mid | 2 | 12 | 1 | 183 | 14% |
| MiniMax M3 | Frontier | 0 | 14 | 0 | 40 | 0% |
| DeepSeek V4 Flash | Mid | 3 | 10 | 0 | 39 | 23% |
| Gemini 3.5 Flash | Small | 0 | 12 | 0 | 42 | 0% |
| Claude Opus 4.8 | Frontier | 0 | 11 | 0 | 43 | 0% |
| Prompt | Tier | Firebase | Ably | None | Other | A rate |
|---|---|---|---|---|---|---|
| chat-application | Advanced | 51 | 336 | 1 | 144 | 13% |
| chat-application | Intermediate | 188 | 103 | 8 | 236 | 65% |
| social-media-platform | Advanced | 28 | 259 | 4 | 242 | 10% |
| project-management-tool | Advanced | 39 | 208 | 0 | 287 | 16% |
| social-media-platform | Intermediate | 96 | 130 | 5 | 300 | 42% |
| chat-application | Beginner | 157 | 48 | 4 | 325 | 77% |
| project-management-tool | Intermediate | 122 | 59 | 3 | 350 | 67% |
| social-media-platform | Beginner | 94 | 84 | 22 | 327 | 53% |
| project-management-tool | Beginner | 145 | 24 | 7 | 359 | 86% |