| Metric | Value |
|---|---|
| tRPC wins | 223 |
| Next.js wins | 258 |
| Abstains (no tool) | 569 |
| Other tool chosen | 3566 |
| Decisive cases | 481 |
| tRPC win rate (unweighted) | 46.4% |
| 95% CI | 42.0% - 50.8% |
| tRPC win rate (weighted) | 46.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | tRPC | Next.js | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Opus 4.6 | Frontier | 40 | 34 | 11 | 167 | 54% |
| Claude Sonnet 4.6 | Frontier | 47 | 17 | 5 | 182 | 73% |
| MiniMax M2.7 | Frontier | 23 | 25 | 27 | 159 | 48% |
| GPT 5.4 Mini | Mid | 30 | 13 | 12 | 168 | 70% |
| DeepSeek V3.2 | Mid | 7 | 35 | 27 | 176 | 17% |
| Kimi K2.5 | Frontier | 37 | 3 | 33 | 163 | 93% |
| Gemini 2.5 Pro | Frontier | 19 | 17 | 16 | 198 | 53% |
| Claude Haiku 4.5 | Small | 4 | 28 | 15 | 189 | 13% |
| GPT 5.4 | Frontier | 9 | 17 | 21 | 200 | 35% |
| DeepSeek R1 0528 | Frontier | 0 | 17 | 54 | 180 | 0% |
| GPT 5.3 Codex | Frontier | 0 | 15 | 9 | 226 | 0% |
| MiMo V2 Pro | Frontier | 0 | 13 | 26 | 212 | 0% |
| Mistral Small 4 | Mid | 0 | 11 | 6 | 212 | 0% |
| GLM 5 Turbo | Frontier | 6 | 1 | 141 | 103 | 86% |
| Llama 4 Scout | Small | 1 | 3 | 11 | 212 | 25% |
| Devstral 2 2512 | Mid | 0 | 4 | 37 | 202 | 0% |
| Llama 4 Maverick | Frontier | 0 | 4 | 4 | 243 | 0% |
| Qwen3 Coder Next | Mid | 0 | 1 | 79 | 162 | 0% |
| Gemini 2.5 Flash | Small | 0 | 0 | 35 | 212 | n/a |
| Prompt | Tier | tRPC | Next.js | None | Other | A rate |
|---|---|---|---|---|---|---|
| url-shortener | Beginner | 27 | 139 | 88 | 136 | 16% |
| multi-tenant-crm | Beginner | 90 | 15 | 107 | 175 | 86% |
| url-shortener | Intermediate | 32 | 49 | 65 | 240 | 40% |
| multi-tenant-crm | Intermediate | 67 | 3 | 74 | 237 | 96% |
| weather-dashboard | Advanced | 3 | 39 | 4 | 338 | 7% |
| weather-dashboard | Intermediate | 0 | 13 | 1 | 383 | 0% |
| multi-tenant-crm | Advanced | 2 | 0 | 30 | 362 | 100% |
| url-shortener | Advanced | 2 | 0 | 36 | 353 | 100% |
| ai-revenue-ops-copilot | Intermediate | 0 | 0 | 72 | 300 | n/a |
| ai-revenue-ops-copilot | Beginner | 0 | 0 | 24 | 337 | n/a |
| ai-revenue-ops-copilot | Advanced | 0 | 0 | 68 | 306 | n/a |
| weather-dashboard | Beginner | 0 | 0 | 0 | 399 | n/a |
