| Metric | Value |
|---|---|
| Next.js wins | 306 |
| Kong wins | 377 |
| Abstains (no tool) | 881 |
| Other tool chosen | 4410 |
| Decisive cases | 683 |
| Next.js win rate (unweighted) | 44.8% |
| 95% CI | 41.1% - 48.6% |
| Next.js win rate (weighted) | 44.8% |
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 | 35 | 45 | 17 | 211 | 44% |
| Claude Sonnet 4.6 | Frontier | 22 | 47 | 12 | 242 | 32% |
| Claude Haiku 4.5 | Small | 32 | 33 | 41 | 200 | 49% |
| Gemini 2.5 Pro | Frontier | 27 | 21 | 33 | 241 | 56% |
| GPT 5.4 | Frontier | 19 | 29 | 38 | 217 | 40% |
| GPT 5.3 Codex | Frontier | 16 | 31 | 22 | 253 | 34% |
| Kimi K2.5 | Frontier | 3 | 43 | 51 | 195 | 7% |
| MiniMax M2.7 | Frontier | 29 | 16 | 40 | 205 | 64% |
| DeepSeek V3.2 | Mid | 40 | 2 | 36 | 224 | 95% |
| GPT 5.4 Mini | Mid | 18 | 24 | 21 | 227 | 43% |
| Devstral 2 2512 | Mid | 5 | 24 | 55 | 230 | 17% |
| MiMo V2 Pro | Frontier | 15 | 11 | 38 | 244 | 58% |
| DeepSeek R1 0528 | Frontier | 20 | 2 | 80 | 221 | 91% |
| Gemini 2.5 Flash | Small | 0 | 22 | 52 | 228 | 0% |
| Mistral Small 4 | Mid | 13 | 1 | 7 | 279 | 93% |
| GLM 5 Turbo | Frontier | 1 | 11 | 168 | 128 | 8% |
| Qwen3 Coder Next | Mid | 1 | 7 | 101 | 201 | 13% |
| Llama 4 Maverick | Frontier | 4 | 0 | 16 | 302 | 100% |
| Llama 4 Scout | Small | 3 | 0 | 23 | 270 | 100% |
| MiMo V2.5 Pro | Frontier | 2 | 1 | 2 | 10 | 67% |
| GPT 5.5 | Frontier | 1 | 2 | 1 | 11 | 33% |
| Claude Opus 4.8 | Frontier | 0 | 2 | 6 | 7 | 0% |
| DeepSeek V4 Pro | Frontier | 0 | 1 | 6 | 7 | 0% |
| GLM 5.2 | Frontier | 0 | 1 | 2 | 12 | 0% |
| Kimi K2.7 Code | Frontier | 0 | 1 | 2 | 12 | 0% |
| DeepSeek V4 Flash | Mid | 0 | 0 | 3 | 11 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 5 | 10 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 3 | 12 | n/a |
| Prompt | Tier | Next.js | Kong | None | Other | A rate |
|---|---|---|---|---|---|---|
| multi-tenant-crm | Advanced | 1 | 206 | 32 | 194 | 0% |
| url-shortener | Beginner | 152 | 0 | 99 | 178 | 100% |
| url-shortener | Advanced | 0 | 111 | 38 | 281 | 0% |
| url-shortener | Intermediate | 51 | 1 | 74 | 298 | 98% |
| multi-tenant-crm | Advanced | 0 | 45 | 9 | 41 | 0% |
| weather-dashboard | Advanced | 44 | 0 | 4 | 373 | 100% |
| multi-tenant-crm | Beginner | 18 | 0 | 118 | 290 | 100% |
| weather-dashboard | Intermediate | 14 | 0 | 1 | 420 | 100% |
| url-shortener | Advanced | 0 | 10 | 15 | 68 | 0% |
| url-shortener | Intermediate | 6 | 0 | 33 | 55 | 100% |
| url-shortener | Beginner | 5 | 0 | 66 | 24 | 100% |
| weather-dashboard | Advanced | 5 | 0 | 2 | 87 | 100% |
| multi-tenant-crm | Intermediate | 4 | 1 | 89 | 325 | 80% |
| multi-tenant-crm | Beginner | 3 | 0 | 60 | 31 | 100% |
| multi-tenant-crm | Intermediate | 1 | 1 | 40 | 52 | 50% |
| ai-revenue-ops-copilot | Advanced | 0 | 2 | 75 | 334 | 0% |
| full-stack-web-app | Beginner | 1 | 0 | 13 | 5 | 100% |
| full-stack-web-app | Intermediate | 1 | 0 | 5 | 11 | 100% |
| ai-revenue-ops-copilot | Intermediate | 0 | 0 | 82 | 328 | n/a |
| ai-revenue-ops-copilot | Beginner | 0 | 0 | 24 | 373 | n/a |
| full-stack-web-app | Advanced | 0 | 0 | 0 | 16 | n/a |
| weather-dashboard | Beginner | 0 | 0 | 0 | 95 | n/a |
| weather-dashboard | Intermediate | 0 | 0 | 2 | 93 | n/a |
| weather-dashboard | Beginner | 0 | 0 | 0 | 438 | n/a |