| Metric | Value |
|---|---|
| Express wins | 27 |
| Next.js wins | 94 |
| Abstains (no tool) | 4 |
| Other tool chosen | 912 |
| Decisive cases | 121 |
| Express win rate (unweighted) | 22.3% |
| 95% CI | 15.8% - 30.5% |
| Express win rate (weighted) | 22.3% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Express | Next.js | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 1 | 3 | 0 | 42 | 25% |
| DeepSeek Pro 4–4 0813 | Frontier | 1 | 1 | 0 | 51 | 50% |
| DeepSeek R1 | Frontier | 2 | 0 | 1 | 49 | 100% |
| Devstral | Mid | 0 | 4 | 0 | 38 | 0% |
| Gemini Flash 2.5–3.8 | Small | 0 | 3 | 1 | 50 | 0% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 0 | 8 | 1 | 45 | 0% |
| GLM 5 Turbo–5.3 | Frontier | 0 | 8 | 0 | 46 | 0% |
| GPT 5.4–6 Astra | Frontier | 0 | 4 | 0 | 50 | 0% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 0 | 1 | 0 | 53 | 0% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 0 | 7 | 0 | 46 | 0% |
| Haiku | Small | 1 | 0 | 0 | 44 | 100% |
| Kimi 2.5–3 | Frontier | 0 | 8 | 0 | 45 | 0% |
| Llama Maverick | Frontier | 7 | 0 | 1 | 46 | 100% |
| Llama Scout | Small | 12 | 0 | 0 | 42 | 100% |
| MiMo Pro 2–2.6 | Frontier | 2 | 0 | 0 | 52 | 100% |
| MiniMax M 2.7–3 | Frontier | 0 | 23 | 0 | 31 | 0% |
| Mistral Small | Mid | 0 | 15 | 0 | 30 | 0% |
| Opus 4.6–5.5 | Frontier | 0 | 1 | 0 | 53 | 0% |
| Qwen Coder | Mid | 1 | 8 | 0 | 45 | 11% |
| Sonnet 4.6–5.5 | Frontier | 0 | 0 | 0 | 54 | n/a |
| Prompt | Tier | Express | Next.js | None | Other | A rate |
|---|---|---|---|---|---|---|
| full-stack-web-app | Beginner | 12 | 55 | 0 | 111 | 18% |
| full-stack-web-app | Intermediate | 12 | 31 | 0 | 133 | 28% |
| full-stack-web-app | Advanced | 3 | 7 | 1 | 138 | 30% |
| ai-agent-application | Beginner | 0 | 1 | 0 | 177 | 0% |
| ai-agent-application | Advanced | 0 | 0 | 2 | 176 | n/a |
| ai-agent-application | Intermediate | 0 | 0 | 1 | 177 | n/a |
