| Metric | Value |
|---|---|
| Express wins | 92 |
| Postman wins | 98 |
| Abstains (no tool) | 879 |
| Other tool chosen | 5459 |
| Decisive cases | 190 |
| Express win rate (unweighted) | 48.4% |
| 95% CI | 41.4% - 55.5% |
| Express win rate (weighted) | 48.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Express | Postman | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 0 | 40 | 16 | 287 | 0% |
| DeepSeek R1 0528 | Frontier | 38 | 0 | 82 | 232 | 100% |
| Llama 4 Scout | Small | 24 | 10 | 26 | 260 | 71% |
| Mistral Small 4 | Mid | 0 | 18 | 11 | 290 | 0% |
| MiMo V2 Pro | Frontier | 16 | 1 | 26 | 220 | 94% |
| MiMo V2.5 Pro | Frontier | 8 | 1 | 9 | 71 | 89% |
| GPT 5.4 Mini | Mid | 0 | 9 | 17 | 282 | 0% |
| Gemini 2.5 Flash | Small | 0 | 6 | 38 | 214 | 0% |
| Gemini 2.5 Pro | Frontier | 0 | 5 | 29 | 318 | 0% |
| MiniMax M2.7 | Frontier | 4 | 0 | 28 | 214 | 100% |
| Claude Haiku 4.5 | Small | 0 | 3 | 18 | 308 | 0% |
| DeepSeek V3.2 | Mid | 0 | 3 | 28 | 226 | 0% |
| DeepSeek V4 Flash | Mid | 2 | 0 | 13 | 67 | 100% |
| Devstral 2 2512 | Mid | 0 | 1 | 51 | 277 | 0% |
| GPT 5.4 | Frontier | 0 | 1 | 23 | 234 | 0% |
| Claude Opus 4.6 | Frontier | 0 | 0 | 13 | 250 | n/a |
| Claude Opus 4.8 | Frontier | 0 | 0 | 30 | 58 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 13 | 337 | n/a |
| DeepSeek V4 Pro | Frontier | 0 | 0 | 26 | 59 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 30 | 57 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 148 | 115 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 9 | 81 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 16 | 336 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 9 | 79 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 36 | 212 | n/a |
| Kimi K2.7 Code | Frontier | 0 | 0 | 10 | 79 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 12 | 76 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 112 | 220 | n/a |
| Prompt | Tier | Express | Postman | None | Other | A rate |
|---|---|---|---|---|---|---|
| url-shortener | Intermediate | 17 | 31 | 94 | 378 | 35% |
| multi-tenant-crm | Intermediate | 23 | 4 | 114 | 373 | 85% |
| url-shortener | Advanced | 13 | 14 | 44 | 450 | 48% |
| url-shortener | Beginner | 19 | 0 | 125 | 381 | 100% |
| ai-revenue-ops-copilot | Beginner | 1 | 15 | 27 | 449 | 6% |
| multi-tenant-crm | Beginner | 14 | 1 | 145 | 364 | 93% |
| ai-revenue-ops-copilot | Intermediate | 0 | 15 | 96 | 396 | 0% |
| ai-revenue-ops-copilot | Advanced | 0 | 15 | 92 | 399 | 0% |
| multi-tenant-crm | Advanced | 2 | 3 | 36 | 489 | 40% |
| weather-dashboard | Advanced | 2 | 0 | 6 | 508 | 100% |
| full-stack-web-app | Intermediate | 1 | 0 | 28 | 64 | 100% |
| full-stack-web-app | Advanced | 0 | 0 | 8 | 86 | n/a |
| full-stack-web-app | Beginner | 0 | 0 | 63 | 54 | n/a |
| weather-dashboard | Beginner | 0 | 0 | 0 | 536 | n/a |
| weather-dashboard | Intermediate | 0 | 0 | 1 | 532 | n/a |