| Metric | Value |
|---|---|
| Django wins | 165 |
| NestJS wins | 167 |
| Abstains (no tool) | 4 |
| Other tool chosen | 701 |
| Decisive cases | 332 |
| Django win rate (unweighted) | 49.7% |
| 95% CI | 44.4% - 55.0% |
| Django win rate (weighted) | 49.7% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Django | NestJS | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 8 | 6 | 0 | 32 | 57% |
| DeepSeek Pro 4–4 0813 | Frontier | 9 | 13 | 0 | 31 | 41% |
| DeepSeek R1 | Frontier | 20 | 2 | 1 | 29 | 91% |
| Devstral | Mid | 9 | 4 | 0 | 29 | 69% |
| Gemini Flash 2.5–3.8 | Small | 8 | 14 | 1 | 31 | 36% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 6 | 10 | 1 | 37 | 38% |
| GLM 5 Turbo–5.3 | Frontier | 3 | 15 | 0 | 36 | 17% |
| GPT 5.4–6 Astra | Frontier | 10 | 10 | 0 | 34 | 50% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 15 | 9 | 0 | 30 | 63% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 7 | 13 | 0 | 33 | 35% |
| Haiku | Small | 17 | 0 | 0 | 28 | 100% |
| Kimi 2.5–3 | Frontier | 3 | 14 | 0 | 36 | 18% |
| Llama Maverick | Frontier | 3 | 5 | 1 | 45 | 38% |
| Llama Scout | Small | 7 | 0 | 0 | 47 | 100% |
| MiMo Pro 2–2.6 | Frontier | 14 | 9 | 0 | 31 | 61% |
| MiniMax M 2.7–3 | Frontier | 2 | 2 | 0 | 50 | 50% |
| Mistral Small | Mid | 0 | 2 | 0 | 43 | 0% |
| Opus 4.6–5.5 | Frontier | 12 | 14 | 0 | 28 | 46% |
| Qwen Coder | Mid | 0 | 17 | 0 | 37 | 0% |
| Sonnet 4.6–5.5 | Frontier | 12 | 8 | 0 | 34 | 60% |
| Prompt | Tier | Django | NestJS | None | Other | A rate |
|---|---|---|---|---|---|---|
| full-stack-web-app | Intermediate | 50 | 68 | 0 | 58 | 42% |
| full-stack-web-app | Advanced | 15 | 97 | 1 | 36 | 13% |
| full-stack-web-app | Beginner | 100 | 0 | 0 | 78 | 100% |
| ai-agent-application | Advanced | 0 | 1 | 2 | 175 | 0% |
| ai-agent-application | Intermediate | 0 | 1 | 1 | 176 | 0% |
| ai-agent-application | Beginner | 0 | 0 | 0 | 178 | n/a |
