| Metric | Value |
|---|---|
| Segment wins | 225 |
| Snowflake wins | 255 |
| Abstains (no tool) | 460 |
| Other tool chosen | 7027 |
| Decisive cases | 480 |
| Segment win rate (unweighted) | 46.9% |
| 95% CI | 42.5% - 51.3% |
| Segment win rate (weighted) | 46.9% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Segment | Snowflake | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 36 | 31 | 0 | 321 | 54% |
| Claude Haiku 4.5 | Small | 54 | 0 | 6 | 347 | 100% |
| Mistral Small 4 | Mid | 12 | 31 | 3 | 356 | 28% |
| Gemini 2.5 Flash | Small | 20 | 18 | 21 | 253 | 53% |
| GPT 5.3 Codex | Frontier | 0 | 32 | 1 | 386 | 0% |
| GPT 5.4 Mini | Mid | 20 | 8 | 7 | 384 | 71% |
| MiMo V2 Pro | Frontier | 17 | 9 | 24 | 265 | 65% |
| Qwen3 Coder Next | Mid | 11 | 15 | 5 | 388 | 42% |
| GPT 5.4 | Frontier | 10 | 16 | 0 | 286 | 38% |
| Llama 4 Scout | Small | 2 | 24 | 25 | 367 | 8% |
| Gemini 2.5 Pro | Frontier | 6 | 16 | 23 | 371 | 27% |
| MiniMax M2.7 | Frontier | 11 | 5 | 36 | 252 | 69% |
| DeepSeek V3.2 | Mid | 14 | 1 | 26 | 271 | 93% |
| Kimi K2.7 Code | Frontier | 0 | 11 | 3 | 91 | 0% |
| GLM 5.2 | Frontier | 0 | 9 | 1 | 95 | 0% |
| DeepSeek R1 0528 | Frontier | 4 | 4 | 150 | 260 | 50% |
| MiMo V2.5 Pro | Frontier | 3 | 5 | 13 | 84 | 38% |
| Kimi K2.5 | Frontier | 3 | 4 | 23 | 270 | 43% |
| Claude Opus 4.8 | Frontier | 0 | 6 | 0 | 98 | 0% |
| GPT 5.5 | Frontier | 1 | 4 | 2 | 94 | 20% |
| DeepSeek V4 Pro | Frontier | 1 | 2 | 18 | 83 | 33% |
| Llama 4 Maverick | Frontier | 0 | 2 | 0 | 417 | 0% |
| Claude Sonnet 4.6 | Frontier | 0 | 1 | 1 | 418 | 0% |
| MiniMax M3 | Frontier | 0 | 1 | 3 | 101 | 0% |
| Claude Opus 4.6 | Frontier | 0 | 0 | 1 | 314 | n/a |
| DeepSeek V4 Flash | Mid | 0 | 0 | 5 | 98 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 0 | 105 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 63 | 252 | n/a |
| Prompt | Tier | Segment | Snowflake | None | Other | A rate |
|---|---|---|---|---|---|---|
| multi-tenant-crm | Advanced | 33 | 109 | 37 | 357 | 23% |
| fitness-tracking-app | Advanced | 72 | 56 | 13 | 384 | 56% |
| ai-revenue-ops-copilot | Advanced | 5 | 82 | 15 | 406 | 6% |
| saas-application | Advanced | 69 | 0 | 31 | 436 | 100% |
| ai-revenue-ops-copilot | Intermediate | 19 | 4 | 2 | 504 | 83% |
| url-shortener | Advanced | 11 | 2 | 5 | 515 | 85% |
| saas-application | Intermediate | 12 | 0 | 51 | 472 | 100% |
| multi-tenant-crm | Intermediate | 2 | 0 | 33 | 496 | 100% |
| ai-revenue-ops-copilot | Beginner | 0 | 2 | 5 | 513 | 0% |
| fitness-tracking-app | Intermediate | 1 | 0 | 17 | 519 | 100% |
| url-shortener | Intermediate | 1 | 0 | 75 | 460 | 100% |
| fitness-tracking-app | Beginner | 0 | 0 | 1 | 535 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 47 | 486 | n/a |
| saas-application | Beginner | 0 | 0 | 18 | 519 | n/a |
| url-shortener | Beginner | 0 | 0 | 110 | 425 | n/a |