| Metric | Value |
|---|---|
| Ably wins | 372 |
| Firebase wins | 299 |
| Abstains (no tool) | 18 |
| Other tool chosen | 841 |
| Decisive cases | 671 |
| Ably win rate (unweighted) | 55.4% |
| 95% CI | 51.7% - 59.2% |
| Ably win rate (weighted) | 55.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Ably | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 0 | 80 | 0 | 1 | 0% |
| Llama 4 Scout | Small | 26 | 22 | 0 | 33 | 54% |
| GPT 5.3 Codex | Frontier | 47 | 0 | 0 | 34 | 100% |
| GPT 5.4 Mini | Mid | 41 | 4 | 0 | 36 | 91% |
| DeepSeek R1 0528 | Frontier | 25 | 20 | 13 | 22 | 56% |
| Mistral Small 4 | Mid | 16 | 28 | 0 | 36 | 36% |
| Qwen3 Coder Next | Mid | 0 | 42 | 0 | 39 | 0% |
| GPT 5.4 | Frontier | 34 | 2 | 0 | 42 | 94% |
| Gemini 2.5 Flash | Small | 2 | 34 | 0 | 45 | 6% |
| Claude Sonnet 4.6 | Frontier | 33 | 0 | 0 | 48 | 100% |
| MiniMax M2.7 | Frontier | 11 | 19 | 0 | 51 | 37% |
| Gemini 2.5 Pro | Frontier | 29 | 0 | 0 | 52 | 100% |
| Llama 4 Maverick | Frontier | 29 | 0 | 0 | 52 | 100% |
| Claude Opus 4.6 | Frontier | 27 | 0 | 0 | 53 | 100% |
| Kimi K2.5 | Frontier | 26 | 0 | 3 | 51 | 100% |
| MiMo V2 Pro | Frontier | 3 | 22 | 0 | 56 | 12% |
| Claude Haiku 4.5 | Small | 0 | 25 | 0 | 54 | 0% |
| GLM 5 Turbo | Frontier | 23 | 0 | 2 | 56 | 100% |
| DeepSeek V3.2 | Mid | 0 | 1 | 0 | 80 | 0% |
| Prompt | Tier | Ably | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| chat-application | Advanced | 101 | 14 | 1 | 53 | 88% |
| chat-application | Intermediate | 31 | 65 | 1 | 73 | 32% |
| social-media-platform | Advanced | 77 | 10 | 1 | 82 | 89% |
| project-management-tool | Advanced | 62 | 12 | 0 | 96 | 84% |
| social-media-platform | Intermediate | 38 | 31 | 2 | 99 | 55% |
| chat-application | Beginner | 14 | 51 | 1 | 104 | 22% |
| project-management-tool | Beginner | 7 | 49 | 3 | 111 | 13% |
| project-management-tool | Intermediate | 15 | 40 | 2 | 113 | 27% |
| social-media-platform | Beginner | 27 | 27 | 7 | 110 | 50% |
