| Metric | Value |
|---|---|
| Supabase wins | 1183 |
| Ably wins | 1659 |
| Abstains (no tool) | 75 |
| Other tool chosen | 3661 |
| Decisive cases | 2842 |
| Supabase win rate (unweighted) | 41.6% |
| 95% CI | 39.8% - 43.4% |
| Supabase win rate (weighted) | 41.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | Supabase | Ably | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 225 | 38 | 2 | 79 | 86% |
| DeepSeek Pro 4–4 0813 | Frontier | 28 | 24 | 1 | 17 | 54% |
| DeepSeek R1 | Frontier | 20 | 110 | 50 | 164 | 15% |
| Devstral | Mid | 0 | 5 | 0 | 323 | 0% |
| Gemini Flash 2.5–3.8 | Small | 29 | 32 | 3 | 282 | 48% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 8 | 125 | 0 | 212 | 6% |
| GLM 5 Turbo–5.3 | Frontier | 20 | 108 | 4 | 214 | 16% |
| GPT 5.4–6 Astra | Frontier | 82 | 160 | 0 | 100 | 34% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 103 | 193 | 0 | 49 | 35% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 97 | 164 | 6 | 75 | 37% |
| Haiku | Small | 52 | 0 | 0 | 287 | 100% |
| Kimi 2.5–3 | Frontier | 47 | 127 | 5 | 164 | 27% |
| Llama Maverick | Frontier | 1 | 95 | 0 | 246 | 1% |
| Llama Scout | Small | 7 | 105 | 1 | 226 | 6% |
| MiMo Pro 2–2.6 | Frontier | 43 | 26 | 1 | 274 | 62% |
| MiniMax M 2.7–3 | Frontier | 134 | 53 | 1 | 155 | 72% |
| Mistral Small | Mid | 64 | 74 | 0 | 203 | 46% |
| Opus 4.6–5.5 | Frontier | 62 | 66 | 1 | 216 | 48% |
| Qwen Coder | Mid | 15 | 0 | 0 | 329 | 100% |
| Sonnet 4.6–5.5 | Frontier | 146 | 154 | 0 | 46 | 49% |
| Prompt | Tier | Supabase | Ably | None | Other | A rate |
|---|---|---|---|---|---|---|
| chat-application | Advanced | 23 | 367 | 1 | 179 | 6% |
| project-management-tool | Advanced | 93 | 226 | 0 | 254 | 29% |
| social-media-platform | Advanced | 30 | 284 | 4 | 254 | 10% |
| project-management-tool | Intermediate | 195 | 61 | 4 | 313 | 76% |
| social-media-platform | Beginner | 157 | 90 | 23 | 296 | 64% |
| social-media-platform | Intermediate | 102 | 141 | 6 | 321 | 42% |
| chat-application | Intermediate | 130 | 106 | 9 | 329 | 55% |
| project-management-tool | Beginner | 203 | 26 | 7 | 338 | 89% |
| chat-application | Beginner | 49 | 55 | 4 | 464 | 47% |
| project-management-tool | Advanced | 12 | 68 | 0 | 70 | 15% |
| social-media-platform | Advanced | 4 | 73 | 2 | 90 | 5% |
| chat-application | Advanced | 1 | 75 | 1 | 75 | 1% |
| social-media-platform | Intermediate | 18 | 33 | 1 | 100 | 35% |
| chat-application | Intermediate | 30 | 20 | 2 | 118 | 60% |
| project-management-tool | Beginner | 36 | 8 | 4 | 104 | 82% |
| chat-application | Beginner | 33 | 11 | 3 | 120 | 75% |
| project-management-tool | Intermediate | 34 | 7 | 0 | 111 | 83% |
| social-media-platform | Beginner | 33 | 8 | 4 | 125 | 80% |