| Metric | Value |
|---|---|
| Mux wins | 296 |
| Firebase wins | 984 |
| Abstains (no tool) | 248 |
| Other tool chosen | 14273 |
| Decisive cases | 1280 |
| Mux win rate (unweighted) | 23.1% |
| 95% CI | 20.9% - 25.5% |
| Mux win rate (weighted) | 23.1% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Mux | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 4 | 6 | 32 | 783 | 40% |
| DeepSeek Pro 4–4 0813 | Frontier | 7 | 9 | 1 | 169 | 44% |
| DeepSeek R1 | Frontier | 0 | 154 | 5 | 667 | 0% |
| Devstral | Mid | 0 | 237 | 37 | 509 | 0% |
| Gemini Flash 2.5–3.8 | Small | 7 | 36 | 44 | 741 | 16% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 42 | 1 | 28 | 756 | 98% |
| GLM 5 Turbo–5.3 | Frontier | 18 | 0 | 19 | 791 | 100% |
| GPT 5.4–6 Astra | Frontier | 12 | 13 | 10 | 791 | 48% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 14 | 10 | 4 | 798 | 58% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 3 | 25 | 9 | 784 | 11% |
| Haiku | Small | 1 | 15 | 0 | 806 | 6% |
| Kimi 2.5–3 | Frontier | 45 | 0 | 13 | 767 | 100% |
| Llama Maverick | Frontier | 0 | 0 | 3 | 825 | n/a |
| Llama Scout | Small | 0 | 59 | 26 | 740 | 0% |
| MiMo Pro 2–2.6 | Frontier | 0 | 99 | 6 | 719 | 0% |
| MiniMax M 2.7–3 | Frontier | 31 | 44 | 4 | 747 | 41% |
| Mistral Small | Mid | 0 | 92 | 0 | 702 | 0% |
| Opus 4.6–5.5 | Frontier | 67 | 0 | 2 | 758 | 100% |
| Qwen Coder | Mid | 2 | 177 | 4 | 643 | 1% |
| Sonnet 4.6–5.5 | Frontier | 43 | 7 | 1 | 777 | 86% |
| Prompt | Tier | Mux | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| online-learning-platform | Beginner | 181 | 7 | 28 | 376 | 96% |
| chat-application | Beginner | 0 | 168 | 21 | 405 | 0% |
| chat-application | Intermediate | 0 | 138 | 4 | 454 | 0% |
| project-management-tool | Intermediate | 0 | 99 | 1 | 492 | 0% |
| project-management-tool | Beginner | 0 | 94 | 2 | 497 | 0% |
| social-media-platform | Beginner | 0 | 90 | 1 | 505 | 0% |
| online-learning-platform | Advanced | 77 | 0 | 4 | 501 | 100% |
| chat-application | Beginner | 0 | 62 | 2 | 103 | 0% |
| social-media-platform | Intermediate | 0 | 52 | 1 | 543 | 0% |
| chat-application | Intermediate | 0 | 40 | 0 | 130 | 0% |
| real-estate-website | Intermediate | 0 | 39 | 0 | 557 | 0% |
| social-media-platform | Beginner | 0 | 32 | 0 | 139 | 0% |
| online-learning-platform | Beginner | 26 | 2 | 7 | 134 | 93% |
| real-estate-website | Beginner | 0 | 24 | 4 | 566 | 0% |
| project-management-tool | Intermediate | 0 | 20 | 1 | 131 | 0% |
| chat-application | Advanced | 0 | 19 | 5 | 568 | 0% |
| project-management-tool | Beginner | 0 | 16 | 3 | 133 | 0% |
| project-management-tool | Advanced | 0 | 15 | 4 | 573 | 0% |
| online-learning-platform | Intermediate | 8 | 6 | 1 | 581 | 57% |
| job-board | Beginner | 0 | 13 | 1 | 157 | 0% |
| job-board | Intermediate | 0 | 12 | 0 | 584 | 0% |
| social-media-platform | Intermediate | 0 | 11 | 1 | 140 | 0% |
| real-estate-website | Beginner | 0 | 9 | 9 | 134 | 0% |
| job-board | Beginner | 0 | 5 | 0 | 591 | 0% |
| online-learning-platform | Advanced | 3 | 0 | 0 | 147 | 100% |
| online-learning-platform | Intermediate | 1 | 2 | 0 | 149 | 33% |
| chat-application | Advanced | 0 | 2 | 2 | 148 | 0% |
| job-board | Intermediate | 0 | 2 | 2 | 148 | 0% |
| ecommerce-store | Intermediate | 0 | 1 | 17 | 574 | 0% |
| job-board | Advanced | 0 | 1 | 1 | 588 | 0% |
| job-board | Advanced | 0 | 1 | 0 | 170 | 0% |
| real-estate-website | Intermediate | 0 | 1 | 1 | 150 | 0% |
| social-media-platform | Advanced | 0 | 1 | 5 | 586 | 0% |
| ecommerce-store | Beginner | 0 | 0 | 32 | 119 | n/a |
| ecommerce-store | Beginner | 0 | 0 | 83 | 509 | n/a |
| ecommerce-store | Advanced | 0 | 0 | 1 | 148 | n/a |
| ecommerce-store | Advanced | 0 | 0 | 1 | 594 | n/a |
| ecommerce-store | Intermediate | 0 | 0 | 0 | 169 | n/a |
| project-management-tool | Advanced | 0 | 0 | 0 | 150 | n/a |
| real-estate-website | Advanced | 0 | 0 | 2 | 592 | n/a |
| real-estate-website | Advanced | 0 | 0 | 0 | 169 | n/a |
| social-media-platform | Advanced | 0 | 0 | 1 | 169 | n/a |