| Metric | Value |
|---|---|
| tRPC wins | 494 |
| Kong wins | 554 |
| Abstains (no tool) | 1432 |
| Other tool chosen | 6325 |
| Decisive cases | 1048 |
| tRPC win rate (unweighted) | 47.1% |
| 95% CI | 44.1% - 50.2% |
| tRPC win rate (weighted) | 47.1% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | tRPC | Kong | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 29 | 11 | 62 | 352 | 73% |
| DeepSeek Pro 4–4 0813 | Frontier | 6 | 11 | 37 | 74 | 35% |
| DeepSeek R1 | Frontier | 0 | 3 | 127 | 342 | 0% |
| Devstral | Mid | 1 | 32 | 75 | 322 | 3% |
| Gemini Flash 2.5–3.8 | Small | 5 | 28 | 108 | 323 | 15% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 29 | 29 | 66 | 349 | 50% |
| GLM 5 Turbo–5.3 | Frontier | 29 | 30 | 198 | 214 | 49% |
| GPT 5.4–6 Astra | Frontier | 15 | 41 | 64 | 347 | 27% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 1 | 49 | 45 | 378 | 2% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 55 | 30 | 37 | 296 | 65% |
| Haiku | Small | 10 | 47 | 62 | 328 | 18% |
| Kimi 2.5–3 | Frontier | 76 | 63 | 78 | 239 | 55% |
| Llama Maverick | Frontier | 0 | 0 | 39 | 428 | n/a |
| Llama Scout | Small | 3 | 0 | 42 | 391 | 100% |
| MiMo Pro 2–2.6 | Frontier | 6 | 21 | 66 | 374 | 22% |
| MiniMax M 2.7–3 | Frontier | 64 | 24 | 63 | 301 | 73% |
| Mistral Small | Mid | 3 | 2 | 17 | 414 | 60% |
| Opus 4.6–5.5 | Frontier | 65 | 60 | 67 | 280 | 52% |
| Qwen Coder | Mid | 0 | 13 | 141 | 297 | 0% |
| Sonnet 4.6–5.5 | Frontier | 97 | 60 | 38 | 276 | 62% |
| Prompt | Tier | tRPC | Kong | None | Other | A rate |
|---|---|---|---|---|---|---|
| multi-tenant-crm | Advanced | 2 | 290 | 37 | 258 | 1% |
| url-shortener | Advanced | 4 | 149 | 48 | 377 | 3% |
| multi-tenant-crm | Beginner | 145 | 0 | 169 | 266 | 100% |
| multi-tenant-crm | Intermediate | 86 | 3 | 135 | 346 | 97% |
| multi-tenant-crm | Advanced | 1 | 81 | 17 | 70 | 1% |
| url-shortener | Intermediate | 58 | 2 | 116 | 403 | 97% |
| url-shortener | Beginner | 43 | 0 | 153 | 385 | 100% |
| full-stack-web-app | Intermediate | 39 | 0 | 41 | 60 | 100% |
| url-shortener | Advanced | 5 | 23 | 22 | 100 | 18% |
| multi-tenant-crm | Beginner | 26 | 0 | 107 | 34 | 100% |
| multi-tenant-crm | Intermediate | 24 | 2 | 65 | 60 | 92% |
| full-stack-web-app | Beginner | 21 | 0 | 105 | 49 | 100% |
| weather-dashboard | Advanced | 14 | 0 | 4 | 135 | 100% |
| full-stack-web-app | Advanced | 12 | 0 | 12 | 128 | 100% |
| url-shortener | Intermediate | 7 | 0 | 53 | 90 | 100% |
| weather-dashboard | Advanced | 6 | 0 | 6 | 561 | 100% |
| ai-revenue-ops-copilot | Advanced | 0 | 3 | 97 | 463 | 0% |
| url-shortener | Beginner | 1 | 0 | 111 | 39 | 100% |
| ai-revenue-ops-copilot | Intermediate | 0 | 1 | 103 | 458 | 0% |
| ai-revenue-ops-copilot | Beginner | 0 | 0 | 27 | 524 | n/a |
| weather-dashboard | Beginner | 0 | 0 | 0 | 168 | n/a |
| weather-dashboard | Intermediate | 0 | 0 | 1 | 591 | n/a |
| weather-dashboard | Beginner | 0 | 0 | 0 | 594 | n/a |
| weather-dashboard | Intermediate | 0 | 0 | 3 | 166 | n/a |