| Metric | Value |
|---|---|
| tRPC wins | 369 |
| Kong wins | 400 |
| Abstains (no tool) | 879 |
| Other tool chosen | 4880 |
| Decisive cases | 769 |
| tRPC win rate (unweighted) | 48.0% |
| 95% CI | 44.5% - 51.5% |
| tRPC win rate (weighted) | 48.0% |
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 | 67 | 49 | 13 | 221 | 58% |
| Claude Opus 4.6 | Frontier | 42 | 40 | 13 | 168 | 51% |
| Kimi K2.5 | Frontier | 38 | 35 | 36 | 139 | 52% |
| GPT 5.4 Mini | Mid | 42 | 23 | 17 | 226 | 65% |
| Gemini 2.5 Pro | Frontier | 23 | 20 | 29 | 280 | 53% |
| Claude Haiku 4.5 | Small | 5 | 36 | 18 | 270 | 12% |
| Kimi K2.7 Code | Frontier | 28 | 9 | 10 | 42 | 76% |
| MiniMax M2.7 | Frontier | 24 | 13 | 28 | 181 | 65% |
| GPT 5.4 | Frontier | 9 | 26 | 23 | 200 | 26% |
| GPT 5.3 Codex | Frontier | 1 | 32 | 16 | 303 | 3% |
| MiniMax M3 | Frontier | 25 | 5 | 12 | 46 | 83% |
| GLM 5.2 | Frontier | 18 | 9 | 9 | 54 | 67% |
| Devstral 2 2512 | Mid | 1 | 25 | 51 | 252 | 4% |
| Gemini 2.5 Flash | Small | 0 | 21 | 38 | 199 | 0% |
| DeepSeek V4 Flash | Mid | 7 | 4 | 13 | 58 | 64% |
| MiMo V2.5 Pro | Frontier | 4 | 7 | 9 | 69 | 36% |
| Claude Opus 4.8 | Frontier | 2 | 9 | 30 | 47 | 18% |
| DeepSeek V3.2 | Mid | 8 | 2 | 28 | 219 | 80% |
| GLM 5 Turbo | Frontier | 6 | 4 | 148 | 105 | 60% |
| DeepSeek V4 Pro | Frontier | 5 | 5 | 26 | 49 | 50% |
| GPT 5.5 | Frontier | 4 | 6 | 9 | 69 | 40% |
| MiMo V2 Pro | Frontier | 0 | 9 | 26 | 228 | 0% |
| Gemini 3.5 Flash | Small | 4 | 3 | 30 | 50 | 57% |
| Qwen3 Coder Next | Mid | 0 | 6 | 112 | 214 | 0% |
| Llama 4 Scout | Small | 3 | 0 | 26 | 291 | 100% |
| Mistral Small 4 | Mid | 3 | 0 | 11 | 305 | 100% |
| DeepSeek R1 0528 | Frontier | 0 | 2 | 82 | 268 | 0% |
| Llama 4 Maverick | Frontier | 0 | 0 | 16 | 327 | n/a |
| Prompt | Tier | tRPC | Kong | None | Other | A rate |
|---|---|---|---|---|---|---|
| multi-tenant-crm | Advanced | 2 | 260 | 36 | 232 | 1% |
| url-shortener | Advanced | 3 | 134 | 44 | 340 | 2% |
| multi-tenant-crm | Beginner | 130 | 0 | 145 | 249 | 100% |
| multi-tenant-crm | Intermediate | 83 | 1 | 114 | 316 | 99% |
| url-shortener | Intermediate | 53 | 1 | 94 | 372 | 98% |
| url-shortener | Beginner | 39 | 0 | 125 | 361 | 100% |
| full-stack-web-app | Intermediate | 26 | 0 | 28 | 39 | 100% |
| full-stack-web-app | Beginner | 16 | 0 | 63 | 38 | 100% |
| full-stack-web-app | Advanced | 11 | 0 | 8 | 75 | 100% |
| weather-dashboard | Advanced | 6 | 0 | 6 | 504 | 100% |
| ai-revenue-ops-copilot | Advanced | 0 | 3 | 92 | 411 | 0% |
| ai-revenue-ops-copilot | Intermediate | 0 | 1 | 96 | 410 | 0% |
| ai-revenue-ops-copilot | Beginner | 0 | 0 | 27 | 465 | n/a |
| weather-dashboard | Beginner | 0 | 0 | 0 | 536 | n/a |
| weather-dashboard | Intermediate | 0 | 0 | 1 | 532 | n/a |