| Metric | Value |
|---|---|
| Next.js wins | 358 |
| tRPC wins | 381 |
| Abstains (no tool) | 896 |
| Other tool chosen | 4944 |
| Decisive cases | 739 |
| Next.js win rate (unweighted) | 48.4% |
| 95% CI | 44.9% - 52.0% |
| Next.js win rate (weighted) | 48.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Next.js | tRPC | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Sonnet 4.6 | Frontier | 22 | 68 | 14 | 249 | 24% |
| Claude Opus 4.6 | Frontier | 32 | 40 | 13 | 166 | 44% |
| GPT 5.4 Mini | Mid | 20 | 40 | 17 | 232 | 33% |
| Gemini 2.5 Pro | Frontier | 29 | 26 | 30 | 270 | 53% |
| MiniMax M2.7 | Frontier | 26 | 23 | 25 | 161 | 53% |
| Claude Haiku 4.5 | Small | 41 | 7 | 18 | 265 | 85% |
| DeepSeek V3.2 | Mid | 37 | 8 | 26 | 175 | 82% |
| Kimi K2.5 | Frontier | 3 | 37 | 35 | 165 | 8% |
| Kimi K2.7 Code | Frontier | 1 | 33 | 10 | 60 | 3% |
| MiniMax M3 | Frontier | 1 | 29 | 13 | 59 | 3% |
| GPT 5.4 | Frontier | 17 | 9 | 22 | 198 | 65% |
| DeepSeek R1 0528 | Frontier | 22 | 0 | 84 | 248 | 100% |
| Mistral Small 4 | Mid | 19 | 3 | 12 | 288 | 86% |
| GPT 5.5 | Frontier | 15 | 6 | 10 | 72 | 71% |
| GLM 5.2 | Frontier | 2 | 19 | 11 | 72 | 10% |
| GPT 5.3 Codex | Frontier | 19 | 1 | 17 | 318 | 95% |
| MiMo V2 Pro | Frontier | 15 | 0 | 24 | 212 | 100% |
| DeepSeek V4 Flash | Mid | 4 | 8 | 14 | 69 | 33% |
| MiMo V2.5 Pro | Frontier | 6 | 4 | 11 | 82 | 60% |
| Llama 4 Scout | Small | 5 | 3 | 30 | 284 | 63% |
| Gemini 3.5 Flash | Small | 4 | 4 | 35 | 58 | 50% |
| Devstral 2 2512 | Mid | 6 | 1 | 49 | 262 | 86% |
| DeepSeek V4 Pro | Frontier | 2 | 5 | 32 | 61 | 29% |
| GLM 5 Turbo | Frontier | 1 | 5 | 142 | 103 | 17% |
| Llama 4 Maverick | Frontier | 4 | 0 | 17 | 323 | 100% |
| Qwen3 Coder Next | Mid | 4 | 0 | 113 | 218 | 100% |
| Claude Opus 4.8 | Frontier | 1 | 2 | 36 | 64 | 33% |
| Gemini 2.5 Flash | Small | 0 | 0 | 36 | 210 | n/a |
| Prompt | Tier | Next.js | tRPC | None | Other | A rate |
|---|---|---|---|---|---|---|
| url-shortener | Beginner | 183 | 41 | 125 | 173 | 82% |
| multi-tenant-crm | Beginner | 25 | 133 | 148 | 219 | 16% |
| url-shortener | Intermediate | 69 | 55 | 93 | 305 | 56% |
| multi-tenant-crm | Intermediate | 5 | 81 | 112 | 318 | 6% |
| weather-dashboard | Advanced | 46 | 6 | 6 | 457 | 88% |
| full-stack-web-app | Intermediate | 5 | 30 | 35 | 38 | 14% |
| full-stack-web-app | Beginner | 8 | 19 | 74 | 34 | 30% |
| weather-dashboard | Intermediate | 14 | 0 | 1 | 518 | 100% |
| full-stack-web-app | Advanced | 2 | 11 | 11 | 84 | 15% |
| multi-tenant-crm | Advanced | 1 | 2 | 35 | 491 | 33% |
| url-shortener | Advanced | 0 | 3 | 43 | 475 | 0% |
| ai-revenue-ops-copilot | Intermediate | 0 | 0 | 97 | 410 | n/a |
| ai-revenue-ops-copilot | Beginner | 0 | 0 | 26 | 468 | n/a |
| ai-revenue-ops-copilot | Advanced | 0 | 0 | 90 | 418 | n/a |
| weather-dashboard | Beginner | 0 | 0 | 0 | 536 | n/a |