| Metric | Value |
|---|---|
| Kong wins | 554 |
| FastAPI wins | 614 |
| Abstains (no tool) | 1432 |
| Other tool chosen | 6205 |
| Decisive cases | 1168 |
| Kong win rate (unweighted) | 47.4% |
| 95% CI | 44.6% - 50.3% |
| Kong win rate (weighted) | 47.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Kong | FastAPI | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 11 | 45 | 62 | 336 | 20% |
| DeepSeek Pro 4–4 0813 | Frontier | 11 | 6 | 37 | 74 | 65% |
| DeepSeek R1 | Frontier | 3 | 70 | 127 | 272 | 4% |
| Devstral | Mid | 32 | 36 | 75 | 287 | 47% |
| Gemini Flash 2.5–3.8 | Small | 28 | 19 | 108 | 309 | 60% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 29 | 42 | 66 | 336 | 41% |
| GLM 5 Turbo–5.3 | Frontier | 30 | 15 | 198 | 228 | 67% |
| GPT 5.4–6 Astra | Frontier | 41 | 56 | 64 | 306 | 42% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 49 | 57 | 45 | 322 | 46% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 30 | 3 | 37 | 348 | 91% |
| Haiku | Small | 47 | 35 | 62 | 303 | 57% |
| Kimi 2.5–3 | Frontier | 63 | 12 | 78 | 303 | 84% |
| Llama Maverick | Frontier | 0 | 5 | 39 | 423 | 0% |
| Llama Scout | Small | 0 | 3 | 42 | 391 | 0% |
| MiMo Pro 2–2.6 | Frontier | 21 | 29 | 66 | 351 | 42% |
| MiniMax M 2.7–3 | Frontier | 24 | 37 | 63 | 328 | 39% |
| Mistral Small | Mid | 2 | 63 | 17 | 354 | 3% |
| Opus 4.6–5.5 | Frontier | 60 | 32 | 67 | 313 | 65% |
| Qwen Coder | Mid | 13 | 46 | 141 | 251 | 22% |
| Sonnet 4.6–5.5 | Frontier | 60 | 3 | 38 | 370 | 95% |
| Prompt | Tier | Kong | FastAPI | None | Other | A rate |
|---|---|---|---|---|---|---|
| multi-tenant-crm | Advanced | 290 | 6 | 37 | 254 | 98% |
| url-shortener | Advanced | 149 | 122 | 48 | 259 | 55% |
| ai-revenue-ops-copilot | Advanced | 3 | 138 | 97 | 325 | 2% |
| multi-tenant-crm | Advanced | 81 | 5 | 17 | 66 | 94% |
| url-shortener | Intermediate | 2 | 70 | 116 | 391 | 3% |
| url-shortener | Advanced | 23 | 48 | 22 | 57 | 32% |
| ai-revenue-ops-copilot | Intermediate | 1 | 62 | 103 | 396 | 2% |
| ai-revenue-ops-copilot | Beginner | 0 | 62 | 27 | 462 | 0% |
| url-shortener | Intermediate | 0 | 27 | 53 | 70 | 0% |
| multi-tenant-crm | Intermediate | 3 | 17 | 135 | 415 | 15% |
| url-shortener | Beginner | 0 | 16 | 153 | 412 | 0% |
| weather-dashboard | Advanced | 0 | 15 | 6 | 552 | 0% |
| multi-tenant-crm | Intermediate | 2 | 9 | 65 | 75 | 18% |
| url-shortener | Beginner | 0 | 7 | 111 | 33 | 0% |
| weather-dashboard | Advanced | 0 | 6 | 4 | 143 | 0% |
| full-stack-web-app | Advanced | 0 | 3 | 12 | 137 | 0% |
| multi-tenant-crm | Beginner | 0 | 1 | 169 | 410 | 0% |
| full-stack-web-app | Beginner | 0 | 0 | 105 | 70 | n/a |
| full-stack-web-app | Intermediate | 0 | 0 | 41 | 99 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 107 | 60 | 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 |