Leading: Supabase (52.4%)
| Metric | Value |
|---|---|
| Salesforce API wins | 151 |
| Supabase wins | 166 |
| Abstains (no tool) | 896 |
| Other tool chosen | 5366 |
| Decisive cases | 317 |
| Salesforce API win rate (unweighted) | 47.6% |
| 95% CI | 42.2% - 53.1% |
| Salesforce API win rate (weighted) | 47.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Salesforce API | Supabase | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek V3.2 | Mid | 17 | 45 | 26 | 158 | 27% |
| Qwen3 Coder Next | Mid | 0 | 40 | 113 | 182 | 0% |
| Claude Haiku 4.5 | Small | 22 | 5 | 18 | 286 | 81% |
| MiniMax M2.7 | Frontier | 17 | 6 | 25 | 187 | 74% |
| Llama 4 Maverick | Frontier | 22 | 0 | 17 | 305 | 100% |
| Gemini 2.5 Pro | Frontier | 0 | 21 | 30 | 304 | 0% |
| Gemini 2.5 Flash | Small | 18 | 2 | 36 | 190 | 90% |
| GPT 5.4 Mini | Mid | 13 | 7 | 17 | 272 | 65% |
| Llama 4 Scout | Small | 17 | 0 | 30 | 275 | 100% |
| GPT 5.4 | Frontier | 12 | 2 | 22 | 210 | 86% |
| MiMo V2 Pro | Frontier | 4 | 5 | 24 | 218 | 44% |
| Claude Sonnet 4.6 | Frontier | 3 | 5 | 14 | 331 | 38% |
| Claude Opus 4.6 | Frontier | 0 | 8 | 13 | 230 | 0% |
| DeepSeek V4 Pro | Frontier | 0 | 7 | 32 | 61 | 0% |
| GPT 5.3 Codex | Frontier | 0 | 7 | 17 | 331 | 0% |
| DeepSeek V4 Flash | Mid | 2 | 2 | 14 | 77 | 50% |
| MiniMax M3 | Frontier | 2 | 0 | 13 | 87 | 100% |
| Mistral Small 4 | Mid | 0 | 2 | 12 | 308 | 0% |
| Devstral 2 2512 | Mid | 1 | 0 | 49 | 268 | 100% |
| MiMo V2.5 Pro | Frontier | 1 | 0 | 11 | 91 | 100% |
| DeepSeek R1 0528 | Frontier | 0 | 1 | 84 | 269 | 0% |
| GLM 5 Turbo | Frontier | 0 | 1 | 142 | 108 | 0% |
| Claude Opus 4.8 | Frontier | 0 | 0 | 36 | 67 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 35 | 66 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 11 | 93 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 10 | 93 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 35 | 205 | n/a |
| Kimi K2.7 Code | Frontier | 0 | 0 | 10 | 94 | n/a |
| Prompt | Tier | Salesforce API | Supabase | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Beginner | 119 | 2 | 26 | 347 | 98% |
| url-shortener | Beginner | 0 | 44 | 125 | 353 | 0% |
| url-shortener | Intermediate | 0 | 40 | 93 | 389 | 0% |
| multi-tenant-crm | Beginner | 7 | 23 | 148 | 347 | 23% |
| ai-revenue-ops-copilot | Intermediate | 22 | 7 | 97 | 381 | 76% |
| multi-tenant-crm | Intermediate | 1 | 27 | 112 | 376 | 4% |
| weather-dashboard | Advanced | 0 | 15 | 6 | 494 | 0% |
| ai-revenue-ops-copilot | Advanced | 2 | 3 | 90 | 413 | 40% |
| full-stack-web-app | Beginner | 0 | 2 | 74 | 59 | 0% |
| url-shortener | Advanced | 0 | 2 | 43 | 476 | 0% |
| multi-tenant-crm | Advanced | 0 | 1 | 35 | 493 | 0% |
| full-stack-web-app | Advanced | 0 | 0 | 11 | 97 | n/a |
| full-stack-web-app | Intermediate | 0 | 0 | 35 | 73 | n/a |
| weather-dashboard | Beginner | 0 | 0 | 0 | 536 | n/a |
| weather-dashboard | Intermediate | 0 | 0 | 1 | 532 | n/a |