| Metric | Value |
|---|---|
| Next.js wins | 62 |
| Django wins | 109 |
| Abstains (no tool) | 4 |
| Other tool chosen | 511 |
| Decisive cases | 171 |
| Next.js win rate (unweighted) | 36.3% |
| 95% CI | 29.4% - 43.7% |
| Next.js win rate (weighted) | 36.3% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Next.js | Django | None | Other | A rate |
|---|---|---|---|---|---|---|
| MiniMax M3 | Frontier | 16 | 2 | 0 | 18 | 89% |
| DeepSeek R1 0528 | Frontier | 0 | 14 | 1 | 20 | 0% |
| Devstral 2 2512 | Mid | 4 | 7 | 0 | 19 | 36% |
| Claude Haiku 4.5 | Small | 0 | 11 | 0 | 19 | 0% |
| MiMo V2.5 Pro | Frontier | 0 | 10 | 0 | 26 | 0% |
| Mistral Small 4 | Mid | 9 | 0 | 0 | 21 | 100% |
| Gemini 2.5 Pro | Frontier | 3 | 6 | 1 | 26 | 33% |
| Claude Opus 4.8 | Frontier | 0 | 9 | 0 | 27 | 0% |
| GPT 5.4 Mini | Mid | 6 | 2 | 0 | 27 | 75% |
| Gemini 3.5 Flash | Small | 2 | 6 | 1 | 27 | 25% |
| DeepSeek V4 Flash | Mid | 1 | 7 | 0 | 22 | 13% |
| GPT 5.3 Codex | Frontier | 1 | 7 | 0 | 28 | 13% |
| GLM 5.2 | Frontier | 6 | 1 | 0 | 29 | 86% |
| Kimi K2.7 Code | Frontier | 6 | 1 | 0 | 28 | 86% |
| GPT 5.5 | Frontier | 3 | 4 | 0 | 29 | 43% |
| DeepSeek V4 Pro | Frontier | 1 | 6 | 0 | 28 | 14% |
| Claude Sonnet 4.6 | Frontier | 0 | 7 | 0 | 29 | 0% |
| Llama 4 Scout | Small | 0 | 7 | 0 | 29 | 0% |
| Qwen3 Coder Next | Mid | 4 | 0 | 0 | 32 | 100% |
| Llama 4 Maverick | Frontier | 0 | 2 | 1 | 27 | 0% |
| Prompt | Tier | Next.js | Django | None | Other | A rate |
|---|---|---|---|---|---|---|
| full-stack-web-app | Beginner | 35 | 67 | 0 | 17 | 34% |
| full-stack-web-app | Intermediate | 20 | 34 | 0 | 64 | 37% |
| full-stack-web-app | Advanced | 6 | 8 | 1 | 77 | 43% |
| ai-agent-application | Beginner | 1 | 0 | 0 | 118 | 100% |
| ai-agent-application | Advanced | 0 | 0 | 2 | 117 | n/a |
| ai-agent-application | Intermediate | 0 | 0 | 1 | 118 | n/a |
