| Metric | Value |
|---|---|
| Mux wins | 230 |
| Firebase wins | 707 |
| Abstains (no tool) | 172 |
| Other tool chosen | 10116 |
| Decisive cases | 937 |
| Mux win rate (unweighted) | 24.5% |
| 95% CI | 21.9% - 27.4% |
| Mux win rate (weighted) | 24.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Mux | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 0 | 170 | 24 | 370 | 0% |
| Qwen3 Coder Next | Mid | 2 | 121 | 3 | 461 | 2% |
| DeepSeek R1 0528 | Frontier | 0 | 106 | 5 | 476 | 0% |
| MiMo V2 Pro | Frontier | 0 | 66 | 1 | 394 | 0% |
| Mistral Small 4 | Mid | 0 | 63 | 0 | 498 | 0% |
| Llama 4 Scout | Small | 0 | 46 | 15 | 526 | 0% |
| Claude Opus 4.6 | Frontier | 43 | 0 | 0 | 418 | 100% |
| MiniMax M2.7 | Frontier | 10 | 32 | 2 | 418 | 24% |
| Claude Sonnet 4.6 | Frontier | 31 | 7 | 0 | 550 | 82% |
| Gemini 2.5 Pro | Frontier | 35 | 0 | 24 | 529 | 100% |
| Kimi K2.5 | Frontier | 35 | 0 | 10 | 415 | 100% |
| Gemini 2.5 Flash | Small | 0 | 27 | 24 | 411 | 0% |
| GPT 5.3 Codex | Frontier | 13 | 7 | 2 | 566 | 65% |
| GPT 5.4 Mini | Mid | 0 | 17 | 6 | 561 | 0% |
| DeepSeek V4 Pro | Frontier | 6 | 8 | 1 | 109 | 43% |
| GPT 5.4 | Frontier | 4 | 9 | 6 | 442 | 31% |
| Claude Opus 4.8 | Frontier | 12 | 0 | 0 | 114 | 100% |
| MiniMax M3 | Frontier | 12 | 0 | 0 | 114 | 100% |
| Claude Haiku 4.5 | Small | 0 | 11 | 0 | 572 | 0% |
| MiMo V2.5 Pro | Frontier | 0 | 11 | 1 | 114 | 0% |
| GLM 5 Turbo | Frontier | 6 | 0 | 16 | 440 | 100% |
| GLM 5.2 | Frontier | 6 | 0 | 0 | 120 | 100% |
| GPT 5.5 | Frontier | 6 | 0 | 0 | 120 | 100% |
| DeepSeek V4 Flash | Mid | 0 | 5 | 4 | 117 | 0% |
| Gemini 3.5 Flash | Small | 4 | 0 | 0 | 122 | 100% |
| Kimi K2.7 Code | Frontier | 3 | 0 | 2 | 121 | 100% |
| DeepSeek V3.2 | Mid | 2 | 1 | 24 | 432 | 67% |
| Llama 4 Maverick | Frontier | 0 | 0 | 2 | 586 | n/a |
| Prompt | Tier | Mux | Firebase | None | Other | A rate |
|---|---|---|---|---|---|---|
| online-learning-platform | Beginner | 158 | 6 | 27 | 342 | 96% |
| chat-application | Beginner | 0 | 153 | 16 | 366 | 0% |
| chat-application | Intermediate | 0 | 128 | 4 | 405 | 0% |
| project-management-tool | Intermediate | 0 | 94 | 1 | 438 | 0% |
| project-management-tool | Beginner | 0 | 88 | 2 | 444 | 0% |
| social-media-platform | Beginner | 0 | 82 | 1 | 454 | 0% |
| online-learning-platform | Advanced | 65 | 0 | 4 | 457 | 100% |
| social-media-platform | Intermediate | 0 | 47 | 1 | 489 | 0% |
| real-estate-website | Intermediate | 0 | 37 | 0 | 500 | 0% |
| chat-application | Advanced | 0 | 18 | 5 | 510 | 0% |
| real-estate-website | Beginner | 0 | 18 | 3 | 514 | 0% |
| project-management-tool | Advanced | 0 | 13 | 3 | 518 | 0% |
| job-board | Intermediate | 0 | 12 | 0 | 525 | 0% |
| online-learning-platform | Intermediate | 7 | 4 | 1 | 525 | 64% |
| job-board | Beginner | 0 | 4 | 0 | 533 | 0% |
| ecommerce-store | Intermediate | 0 | 1 | 17 | 515 | 0% |
| job-board | Advanced | 0 | 1 | 1 | 530 | 0% |
| social-media-platform | Advanced | 0 | 1 | 4 | 529 | 0% |
| ecommerce-store | Beginner | 0 | 0 | 79 | 454 | n/a |
| ecommerce-store | Advanced | 0 | 0 | 1 | 535 | n/a |
| real-estate-website | Advanced | 0 | 0 | 2 | 533 | n/a |