| Metric | Value |
|---|---|
| Segment wins | 311 |
| Snowflake wins | 308 |
| Abstains (no tool) | 748 |
| Other tool chosen | 9421 |
| Decisive cases | 619 |
| Segment win rate (unweighted) | 50.2% |
| 95% CI | 46.3% - 54.2% |
| Segment win rate (weighted) | 50.2% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Segment | Snowflake | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 18 | 2 | 47 | 495 | 90% |
| DeepSeek Pro 4–4 0813 | Frontier | 1 | 3 | 19 | 111 | 25% |
| DeepSeek R1 | Frontier | 6 | 5 | 205 | 349 | 55% |
| Devstral | Mid | 49 | 40 | 6 | 440 | 55% |
| Gemini Flash 2.5–3.8 | Small | 32 | 19 | 35 | 479 | 63% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 7 | 17 | 48 | 490 | 29% |
| GLM 5 Turbo–5.3 | Frontier | 0 | 11 | 91 | 466 | 0% |
| GPT 5.4–6 Astra | Frontier | 13 | 25 | 12 | 509 | 34% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 0 | 39 | 18 | 510 | 0% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 30 | 14 | 11 | 510 | 68% |
| Haiku | Small | 66 | 0 | 24 | 463 | 100% |
| Kimi 2.5–3 | Frontier | 4 | 16 | 42 | 486 | 20% |
| Llama Maverick | Frontier | 0 | 2 | 0 | 565 | 0% |
| Llama Scout | Small | 3 | 28 | 29 | 506 | 10% |
| MiMo Pro 2–2.6 | Frontier | 23 | 16 | 55 | 471 | 59% |
| MiniMax M 2.7–3 | Frontier | 17 | 7 | 68 | 465 | 71% |
| Mistral Small | Mid | 17 | 38 | 3 | 491 | 31% |
| Opus 4.6–5.5 | Frontier | 0 | 6 | 17 | 544 | 0% |
| Qwen Coder | Mid | 14 | 19 | 8 | 525 | 42% |
| Sonnet 4.6–5.5 | Frontier | 11 | 1 | 10 | 546 | 92% |
| Prompt | Tier | Segment | Snowflake | None | Other | A rate |
|---|---|---|---|---|---|---|
| multi-tenant-crm | Advanced | 37 | 119 | 38 | 401 | 24% |
| fitness-tracking-app | Advanced | 80 | 60 | 15 | 426 | 57% |
| ai-revenue-ops-copilot | Advanced | 5 | 101 | 16 | 442 | 5% |
| saas-application | Advanced | 73 | 0 | 33 | 489 | 100% |
| fitness-tracking-app | Advanced | 23 | 18 | 3 | 125 | 56% |
| saas-application | Advanced | 25 | 0 | 9 | 136 | 100% |
| ai-revenue-ops-copilot | Intermediate | 19 | 4 | 3 | 561 | 83% |
| saas-application | Intermediate | 13 | 0 | 57 | 524 | 100% |
| url-shortener | Advanced | 11 | 2 | 5 | 573 | 85% |
| saas-application | Intermediate | 7 | 0 | 7 | 157 | 100% |
| multi-tenant-crm | Advanced | 4 | 2 | 8 | 156 | 67% |
| saas-application | Beginner | 5 | 0 | 6 | 158 | 100% |
| fitness-tracking-app | Intermediate | 2 | 0 | 19 | 575 | 100% |
| multi-tenant-crm | Intermediate | 2 | 0 | 37 | 550 | 100% |
| ai-revenue-ops-copilot | Beginner | 0 | 2 | 5 | 573 | 0% |
| fitness-tracking-app | Beginner | 1 | 0 | 2 | 167 | 100% |
| multi-tenant-crm | Beginner | 1 | 0 | 57 | 534 | 100% |
| saas-application | Beginner | 1 | 0 | 18 | 577 | 100% |
| url-shortener | Intermediate | 1 | 0 | 85 | 508 | 100% |
| url-shortener | Advanced | 1 | 0 | 5 | 145 | 100% |
| fitness-tracking-app | Beginner | 0 | 0 | 1 | 594 | n/a |
| fitness-tracking-app | Intermediate | 0 | 0 | 20 | 132 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 31 | 137 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 25 | 127 | n/a |
| url-shortener | Beginner | 0 | 0 | 62 | 90 | n/a |
| url-shortener | Beginner | 0 | 0 | 132 | 462 | n/a |
| url-shortener | Intermediate | 0 | 0 | 49 | 102 | n/a |