| Metric | Value |
|---|---|
| Express wins | 23 |
| Next.js wins | 83 |
| Abstains (no tool) | 4 |
| Other tool chosen | 801 |
| Decisive cases | 106 |
| Express win rate (unweighted) | 21.7% |
| 95% CI | 14.9% - 30.5% |
| Express win rate (weighted) | 21.7% |
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 | 2 | 0 | 37 | 33% |
| DeepSeek Pro 4–4 0813 | Frontier | 1 | 1 | 0 | 45 | 50% |
| DeepSeek R1 | Frontier | 2 | 0 | 1 | 43 | 100% |
| Devstral | Mid | 0 | 4 | 0 | 32 | 0% |
| Gemini Flash 2.5–3.8 | Small | 0 | 3 | 1 | 44 | 0% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 0 | 6 | 1 | 41 | 0% |
| GLM 5 Turbo–5.3 | Frontier | 0 | 8 | 0 | 40 | 0% |
| GPT 5.4–6 Astra | Frontier | 0 | 4 | 0 | 44 | 0% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 0 | 1 | 0 | 47 | 0% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 0 | 7 | 0 | 40 | 0% |
| Haiku | Small | 1 | 0 | 0 | 39 | 100% |
| Kimi 2.5–3 | Frontier | 0 | 8 | 0 | 39 | 0% |
| Llama Maverick | Frontier | 6 | 0 | 1 | 33 | 100% |
| Llama Scout | Small | 9 | 0 | 0 | 39 | 100% |
| MiMo Pro 2–2.6 | Frontier | 2 | 0 | 0 | 46 | 100% |
| MiniMax M 2.7–3 | Frontier | 0 | 20 | 0 | 28 | 0% |
| Mistral Small | Mid | 0 | 13 | 0 | 27 | 0% |
| Opus 4.6–5.5 | Frontier | 0 | 0 | 0 | 48 | n/a |
| Qwen Coder | Mid | 1 | 6 | 0 | 41 | 14% |
| Sonnet 4.6–5.5 | Frontier | 0 | 0 | 0 | 48 | n/a |
| Prompt | Tier | Express | Next.js | None | Other | A rate |
|---|---|---|---|---|---|---|
| full-stack-web-app | Beginner | 10 | 50 | 0 | 98 | 17% |
| full-stack-web-app | Intermediate | 11 | 26 | 0 | 119 | 30% |
| full-stack-web-app | Advanced | 2 | 6 | 1 | 114 | 25% |
| ai-agent-application | Beginner | 0 | 1 | 0 | 157 | 0% |
| ai-agent-application | Advanced | 0 | 0 | 2 | 156 | n/a |
| ai-agent-application | Intermediate | 0 | 0 | 1 | 157 | n/a |
