| Metric | Value |
|---|---|
| tRPC wins | 381 |
| Kong wins | 398 |
| Abstains (no tool) | 896 |
| Other tool chosen | 4904 |
| Decisive cases | 779 |
| tRPC win rate (unweighted) | 48.9% |
| 95% CI | 45.4% - 52.4% |
| tRPC win rate (weighted) | 48.9% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | tRPC | Kong | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Sonnet 4.6 | Frontier | 68 | 48 | 14 | 223 | 59% |
| Claude Opus 4.6 | Frontier | 40 | 38 | 13 | 160 | 51% |
| Kimi K2.5 | Frontier | 37 | 33 | 35 | 135 | 53% |
| GPT 5.4 Mini | Mid | 40 | 22 | 17 | 230 | 65% |
| Gemini 2.5 Pro | Frontier | 26 | 19 | 30 | 280 | 58% |
| Claude Haiku 4.5 | Small | 7 | 36 | 18 | 270 | 16% |
| Kimi K2.7 Code | Frontier | 33 | 9 | 10 | 52 | 79% |
| MiniMax M2.7 | Frontier | 23 | 12 | 25 | 175 | 66% |
| GPT 5.3 Codex | Frontier | 1 | 34 | 17 | 303 | 3% |
| MiniMax M3 | Frontier | 29 | 5 | 13 | 55 | 85% |
| GPT 5.4 | Frontier | 9 | 25 | 22 | 190 | 26% |
| GLM 5.2 | Frontier | 19 | 10 | 11 | 64 | 66% |
| Devstral 2 2512 | Mid | 1 | 24 | 49 | 244 | 4% |
| Gemini 2.5 Flash | Small | 0 | 20 | 36 | 190 | 0% |
| DeepSeek V4 Flash | Mid | 8 | 5 | 14 | 68 | 62% |
| GPT 5.5 | Frontier | 6 | 7 | 10 | 80 | 46% |
| DeepSeek V4 Pro | Frontier | 5 | 8 | 32 | 55 | 38% |
| Claude Opus 4.8 | Frontier | 2 | 10 | 36 | 55 | 17% |
| MiMo V2.5 Pro | Frontier | 4 | 7 | 11 | 81 | 36% |
| DeepSeek V3.2 | Mid | 8 | 2 | 26 | 210 | 80% |
| GLM 5 Turbo | Frontier | 5 | 4 | 142 | 100 | 56% |
| MiMo V2 Pro | Frontier | 0 | 9 | 24 | 218 | 0% |
| Gemini 3.5 Flash | Small | 4 | 3 | 35 | 59 | 57% |
| Qwen3 Coder Next | Mid | 0 | 6 | 113 | 216 | 0% |
| Llama 4 Scout | Small | 3 | 0 | 30 | 289 | 100% |
| Mistral Small 4 | Mid | 3 | 0 | 12 | 307 | 100% |
| DeepSeek R1 0528 | Frontier | 0 | 2 | 84 | 268 | 0% |
| Llama 4 Maverick | Frontier | 0 | 0 | 17 | 327 | n/a |
| Prompt | Tier | tRPC | Kong | None | Other | A rate |
|---|---|---|---|---|---|---|
| multi-tenant-crm | Advanced | 2 | 258 | 35 | 234 | 1% |
| url-shortener | Advanced | 3 | 133 | 43 | 342 | 2% |
| multi-tenant-crm | Beginner | 133 | 0 | 148 | 244 | 100% |
| multi-tenant-crm | Intermediate | 81 | 2 | 112 | 321 | 98% |
| url-shortener | Intermediate | 55 | 1 | 93 | 373 | 98% |
| url-shortener | Beginner | 41 | 0 | 125 | 356 | 100% |
| full-stack-web-app | Intermediate | 30 | 0 | 35 | 43 | 100% |
| full-stack-web-app | Beginner | 19 | 0 | 74 | 42 | 100% |
| full-stack-web-app | Advanced | 11 | 0 | 11 | 86 | 100% |
| weather-dashboard | Advanced | 6 | 0 | 6 | 503 | 100% |
| ai-revenue-ops-copilot | Advanced | 0 | 3 | 90 | 415 | 0% |
| ai-revenue-ops-copilot | Intermediate | 0 | 1 | 97 | 409 | 0% |
| ai-revenue-ops-copilot | Beginner | 0 | 0 | 26 | 468 | n/a |
| weather-dashboard | Beginner | 0 | 0 | 0 | 536 | n/a |
| weather-dashboard | Intermediate | 0 | 0 | 1 | 532 | n/a |