| Metric | Value |
|---|---|
| Next.js wins | 248 |
| Kong wins | 275 |
| Abstains (no tool) | 539 |
| Other tool chosen | 3331 |
| Decisive cases | 523 |
| Next.js win rate (unweighted) | 47.4% |
| 95% CI | 43.2% - 51.7% |
| Next.js win rate (weighted) | 47.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Next.js | Kong | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Opus 4.6 | Frontier | 33 | 36 | 11 | 160 | 48% |
| Claude Sonnet 4.6 | Frontier | 16 | 36 | 5 | 182 | 31% |
| Claude Haiku 4.5 | Small | 27 | 24 | 14 | 159 | 53% |
| GPT 5.4 | Frontier | 16 | 23 | 20 | 177 | 41% |
| DeepSeek V3.2 | Mid | 34 | 2 | 26 | 171 | 94% |
| GPT 5.3 Codex | Frontier | 14 | 22 | 9 | 193 | 39% |
| MiniMax M2.7 | Frontier | 23 | 12 | 27 | 161 | 66% |
| Kimi K2.5 | Frontier | 3 | 32 | 30 | 159 | 9% |
| Gemini 2.5 Pro | Frontier | 17 | 17 | 16 | 188 | 50% |
| GPT 5.4 Mini | Mid | 13 | 16 | 11 | 172 | 45% |
| Devstral 2 2512 | Mid | 4 | 19 | 35 | 173 | 17% |
| MiMo V2 Pro | Frontier | 13 | 8 | 23 | 195 | 62% |
| Gemini 2.5 Flash | Small | 0 | 19 | 34 | 182 | 0% |
| DeepSeek R1 0528 | Frontier | 16 | 1 | 50 | 172 | 94% |
| Mistral Small 4 | Mid | 10 | 0 | 6 | 202 | 100% |
| GLM 5 Turbo | Frontier | 1 | 4 | 134 | 100 | 20% |
| Qwen3 Coder Next | Mid | 1 | 4 | 74 | 152 | 20% |
| Llama 4 Maverick | Frontier | 4 | 0 | 4 | 231 | 100% |
| Llama 4 Scout | Small | 3 | 0 | 10 | 202 | 100% |
| Prompt | Tier | Next.js | Kong | None | Other | A rate |
|---|---|---|---|---|---|---|
| multi-tenant-crm | Advanced | 0 | 176 | 28 | 171 | 0% |
| url-shortener | Beginner | 133 | 0 | 81 | 157 | 100% |
| url-shortener | Advanced | 0 | 95 | 35 | 242 | 0% |
| url-shortener | Intermediate | 47 | 1 | 63 | 256 | 98% |
| weather-dashboard | Advanced | 39 | 0 | 4 | 322 | 100% |
| multi-tenant-crm | Beginner | 13 | 0 | 100 | 255 | 100% |
| weather-dashboard | Intermediate | 13 | 0 | 1 | 364 | 100% |
| multi-tenant-crm | Intermediate | 3 | 1 | 70 | 288 | 75% |
| ai-revenue-ops-copilot | Advanced | 0 | 2 | 65 | 290 | 0% |
| ai-revenue-ops-copilot | Intermediate | 0 | 0 | 69 | 285 | n/a |
| ai-revenue-ops-copilot | Beginner | 0 | 0 | 23 | 321 | n/a |
| weather-dashboard | Beginner | 0 | 0 | 0 | 380 | n/a |