| Metric | Value |
|---|---|
| Next.js wins | 94 |
| Django wins | 165 |
| Abstains (no tool) | 4 |
| Other tool chosen | 774 |
| Decisive cases | 259 |
| Next.js win rate (unweighted) | 36.3% |
| 95% CI | 30.7% - 42.3% |
| Next.js win rate (weighted) | 36.3% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Next.js | Django | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 3 | 8 | 0 | 35 | 27% |
| DeepSeek Pro 4–4 0813 | Frontier | 1 | 9 | 0 | 43 | 10% |
| DeepSeek R1 | Frontier | 0 | 20 | 1 | 31 | 0% |
| Devstral | Mid | 4 | 9 | 0 | 29 | 31% |
| Gemini Flash 2.5–3.8 | Small | 3 | 8 | 1 | 42 | 27% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 8 | 6 | 1 | 39 | 57% |
| GLM 5 Turbo–5.3 | Frontier | 8 | 3 | 0 | 43 | 73% |
| GPT 5.4–6 Astra | Frontier | 4 | 10 | 0 | 40 | 29% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 1 | 15 | 0 | 38 | 6% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 7 | 7 | 0 | 39 | 50% |
| Haiku | Small | 0 | 17 | 0 | 28 | 0% |
| Kimi 2.5–3 | Frontier | 8 | 3 | 0 | 42 | 73% |
| Llama Maverick | Frontier | 0 | 3 | 1 | 50 | 0% |
| Llama Scout | Small | 0 | 7 | 0 | 47 | 0% |
| MiMo Pro 2–2.6 | Frontier | 0 | 14 | 0 | 40 | 0% |
| MiniMax M 2.7–3 | Frontier | 23 | 2 | 0 | 29 | 92% |
| Mistral Small | Mid | 15 | 0 | 0 | 30 | 100% |
| Opus 4.6–5.5 | Frontier | 1 | 12 | 0 | 41 | 8% |
| Qwen Coder | Mid | 8 | 0 | 0 | 46 | 100% |
| Sonnet 4.6–5.5 | Frontier | 0 | 12 | 0 | 42 | 0% |
| Prompt | Tier | Next.js | Django | None | Other | A rate |
|---|---|---|---|---|---|---|
| full-stack-web-app | Beginner | 55 | 100 | 0 | 23 | 35% |
| full-stack-web-app | Intermediate | 31 | 50 | 0 | 95 | 38% |
| full-stack-web-app | Advanced | 7 | 15 | 1 | 126 | 32% |
| ai-agent-application | Beginner | 1 | 0 | 0 | 177 | 100% |
| ai-agent-application | Advanced | 0 | 0 | 2 | 176 | n/a |
| ai-agent-application | Intermediate | 0 | 0 | 1 | 177 | n/a |
