| Metric | Value |
|---|---|
| Express wins | 129 |
| Apigee wins | 121 |
| Abstains (no tool) | 1432 |
| Other tool chosen | 7123 |
| Decisive cases | 250 |
| Express win rate (unweighted) | 51.6% |
| 95% CI | 45.4% - 57.7% |
| Express win rate (weighted) | 51.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Express | Apigee | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 2 | 0 | 62 | 390 | 100% |
| DeepSeek Pro 4–4 0813 | Frontier | 0 | 0 | 37 | 91 | n/a |
| DeepSeek R1 | Frontier | 50 | 0 | 127 | 295 | 100% |
| Devstral | Mid | 0 | 0 | 75 | 355 | n/a |
| Gemini Flash 2.5–3.8 | Small | 0 | 4 | 108 | 352 | 0% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 1 | 0 | 66 | 406 | 100% |
| GLM 5 Turbo–5.3 | Frontier | 0 | 0 | 198 | 273 | n/a |
| GPT 5.4–6 Astra | Frontier | 0 | 0 | 64 | 403 | n/a |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 0 | 0 | 45 | 428 | n/a |
| GPT Mini 5.4 Mini–6 Luna | Mid | 0 | 0 | 37 | 381 | n/a |
| Haiku | Small | 0 | 0 | 62 | 385 | n/a |
| Kimi 2.5–3 | Frontier | 0 | 0 | 78 | 378 | n/a |
| Llama Maverick | Frontier | 0 | 73 | 39 | 355 | 0% |
| Llama Scout | Small | 36 | 43 | 42 | 315 | 46% |
| MiMo Pro 2–2.6 | Frontier | 30 | 1 | 66 | 370 | 97% |
| MiniMax M 2.7–3 | Frontier | 7 | 0 | 63 | 382 | 100% |
| Mistral Small | Mid | 0 | 0 | 17 | 419 | n/a |
| Opus 4.6–5.5 | Frontier | 3 | 0 | 67 | 402 | 100% |
| Qwen Coder | Mid | 0 | 0 | 141 | 310 | n/a |
| Sonnet 4.6–5.5 | Frontier | 0 | 0 | 38 | 433 | n/a |
| Prompt | Tier | Express | Apigee | None | Other | A rate |
|---|---|---|---|---|---|---|
| multi-tenant-crm | Advanced | 4 | 56 | 37 | 490 | 7% |
| multi-tenant-crm | Intermediate | 27 | 3 | 135 | 405 | 90% |
| url-shortener | Advanced | 13 | 15 | 48 | 502 | 46% |
| url-shortener | Beginner | 23 | 0 | 153 | 405 | 100% |
| url-shortener | Intermediate | 17 | 1 | 116 | 445 | 94% |
| multi-tenant-crm | Beginner | 16 | 0 | 169 | 395 | 100% |
| ai-revenue-ops-copilot | Intermediate | 0 | 16 | 103 | 443 | 0% |
| ai-revenue-ops-copilot | Advanced | 0 | 15 | 97 | 451 | 0% |
| multi-tenant-crm | Advanced | 0 | 11 | 17 | 141 | 0% |
| multi-tenant-crm | Intermediate | 9 | 0 | 65 | 77 | 100% |
| url-shortener | Advanced | 4 | 3 | 22 | 121 | 57% |
| url-shortener | Intermediate | 6 | 0 | 53 | 91 | 100% |
| url-shortener | Beginner | 3 | 0 | 111 | 37 | 100% |
| weather-dashboard | Advanced | 3 | 0 | 6 | 564 | 100% |
| multi-tenant-crm | Beginner | 2 | 0 | 107 | 58 | 100% |
| ai-revenue-ops-copilot | Beginner | 1 | 0 | 27 | 523 | 100% |
| full-stack-web-app | Intermediate | 1 | 0 | 41 | 98 | 100% |
| weather-dashboard | Advanced | 0 | 1 | 4 | 148 | 0% |
| full-stack-web-app | Beginner | 0 | 0 | 105 | 70 | n/a |
| full-stack-web-app | Advanced | 0 | 0 | 12 | 140 | 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 |