| Metric | Value |
|---|---|
| Segment wins | 232 |
| Snowflake wins | 252 |
| Abstains (no tool) | 459 |
| Other tool chosen | 7022 |
| Decisive cases | 484 |
| Segment win rate (unweighted) | 47.9% |
| 95% CI | 43.5% - 52.4% |
| Segment win rate (weighted) | 47.9% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Segment | Snowflake | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 37 | 32 | 0 | 334 | 54% |
| Claude Haiku 4.5 | Small | 55 | 0 | 5 | 346 | 100% |
| Mistral Small 4 | Mid | 13 | 29 | 3 | 358 | 31% |
| Gemini 2.5 Flash | Small | 21 | 19 | 22 | 265 | 53% |
| GPT 5.3 Codex | Frontier | 0 | 33 | 1 | 385 | 0% |
| GPT 5.4 Mini | Mid | 21 | 9 | 7 | 382 | 70% |
| MiMo V2 Pro | Frontier | 18 | 10 | 25 | 277 | 64% |
| Qwen3 Coder Next | Mid | 12 | 15 | 5 | 388 | 44% |
| GPT 5.4 | Frontier | 10 | 17 | 0 | 300 | 37% |
| Llama 4 Scout | Small | 2 | 23 | 25 | 368 | 8% |
| Gemini 2.5 Pro | Frontier | 6 | 16 | 26 | 368 | 27% |
| MiniMax M2.7 | Frontier | 11 | 6 | 36 | 266 | 65% |
| DeepSeek V3.2 | Mid | 15 | 1 | 27 | 284 | 94% |
| DeepSeek R1 0528 | Frontier | 4 | 5 | 149 | 260 | 44% |
| Kimi K2.7 Code | Frontier | 0 | 9 | 3 | 78 | 0% |
| GLM 5.2 | Frontier | 0 | 8 | 1 | 81 | 0% |
| Kimi K2.5 | Frontier | 3 | 4 | 23 | 281 | 43% |
| MiMo V2.5 Pro | Frontier | 3 | 4 | 11 | 72 | 43% |
| Claude Opus 4.8 | Frontier | 0 | 5 | 0 | 84 | 0% |
| GPT 5.5 | Frontier | 1 | 3 | 1 | 82 | 25% |
| Llama 4 Maverick | Frontier | 0 | 2 | 0 | 417 | 0% |
| DeepSeek V4 Pro | Frontier | 0 | 1 | 15 | 73 | 0% |
| MiniMax M3 | Frontier | 0 | 1 | 3 | 86 | 0% |
| Claude Opus 4.6 | Frontier | 0 | 0 | 1 | 329 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 1 | 419 | n/a |
| DeepSeek V4 Flash | Mid | 0 | 0 | 4 | 84 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 0 | 90 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 65 | 265 | n/a |
| Prompt | Tier | Segment | Snowflake | None | Other | A rate |
|---|---|---|---|---|---|---|
| multi-tenant-crm | Advanced | 34 | 108 | 37 | 357 | 24% |
| fitness-tracking-app | Advanced | 74 | 56 | 13 | 383 | 57% |
| ai-revenue-ops-copilot | Advanced | 5 | 81 | 16 | 404 | 6% |
| saas-application | Advanced | 71 | 0 | 30 | 435 | 100% |
| ai-revenue-ops-copilot | Intermediate | 19 | 3 | 3 | 504 | 86% |
| url-shortener | Advanced | 11 | 2 | 5 | 514 | 85% |
| saas-application | Intermediate | 12 | 0 | 52 | 471 | 100% |
| fitness-tracking-app | Intermediate | 2 | 0 | 16 | 519 | 100% |
| multi-tenant-crm | Intermediate | 2 | 0 | 34 | 494 | 100% |
| ai-revenue-ops-copilot | Beginner | 0 | 2 | 5 | 513 | 0% |
| multi-tenant-crm | Beginner | 1 | 0 | 47 | 486 | 100% |
| url-shortener | Intermediate | 1 | 0 | 75 | 459 | 100% |
| fitness-tracking-app | Beginner | 0 | 0 | 1 | 535 | n/a |
| saas-application | Beginner | 0 | 0 | 16 | 521 | n/a |
| url-shortener | Beginner | 0 | 0 | 109 | 427 | n/a |