| Metric | Value |
|---|---|
| Pusher wins | 680 |
| Supabase wins | 901 |
| Abstains (no tool) | 52 |
| Other tool chosen | 3163 |
| Decisive cases | 1581 |
| Pusher win rate (unweighted) | 43.0% |
| 95% CI | 40.6% - 45.5% |
| Pusher win rate (weighted) | 43.0% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Pusher | Supabase | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek V3.2 | Mid | 8 | 145 | 1 | 35 | 5% |
| Claude Sonnet 4.6 | Frontier | 6 | 113 | 0 | 133 | 5% |
| Gemini 2.5 Pro | Frontier | 107 | 1 | 0 | 144 | 99% |
| Qwen3 Coder Next | Mid | 97 | 11 | 0 | 142 | 90% |
| MiMo V2 Pro | Frontier | 78 | 22 | 0 | 88 | 78% |
| MiniMax M2.7 | Frontier | 10 | 81 | 0 | 96 | 11% |
| GLM 5 Turbo | Frontier | 72 | 9 | 3 | 105 | 89% |
| Mistral Small 4 | Mid | 31 | 49 | 0 | 167 | 39% |
| GPT 5.4 Mini | Mid | 7 | 71 | 4 | 166 | 9% |
| GPT 5.3 Codex | Frontier | 6 | 67 | 0 | 179 | 8% |
| DeepSeek R1 0528 | Frontier | 44 | 16 | 40 | 151 | 73% |
| Claude Opus 4.6 | Frontier | 31 | 26 | 0 | 132 | 54% |
| GPT 5.4 | Frontier | 14 | 37 | 0 | 136 | 27% |
| Claude Haiku 4.5 | Small | 1 | 47 | 0 | 197 | 2% |
| Llama 4 Scout | Small | 40 | 4 | 0 | 204 | 91% |
| DeepSeek V4 Flash | Mid | 12 | 32 | 0 | 17 | 27% |
| MiniMax M3 | Frontier | 17 | 22 | 0 | 24 | 44% |
| Claude Opus 4.8 | Frontier | 7 | 29 | 0 | 27 | 19% |
| Gemini 2.5 Flash | Small | 7 | 24 | 0 | 158 | 23% |
| Gemini 3.5 Flash | Small | 24 | 4 | 0 | 35 | 86% |
| MiMo V2.5 Pro | Frontier | 15 | 13 | 0 | 35 | 54% |
| Llama 4 Maverick | Frontier | 26 | 1 | 0 | 222 | 96% |
| DeepSeek V4 Pro | Frontier | 2 | 24 | 1 | 34 | 8% |
| Kimi K2.5 | Frontier | 2 | 18 | 3 | 164 | 10% |
| GLM 5.2 | Frontier | 12 | 7 | 0 | 44 | 63% |
| Kimi K2.7 Code | Frontier | 2 | 14 | 0 | 47 | 13% |
| GPT 5.5 | Frontier | 0 | 14 | 0 | 49 | 0% |
| Devstral 2 2512 | Mid | 2 | 0 | 0 | 232 | 100% |
| Prompt | Tier | Pusher | Supabase | None | Other | A rate |
|---|---|---|---|---|---|---|
| social-media-platform | Beginner | 120 | 144 | 22 | 241 | 45% |
| project-management-tool | Beginner | 75 | 187 | 7 | 266 | 29% |
| social-media-platform | Intermediate | 163 | 93 | 4 | 271 | 64% |
| project-management-tool | Intermediate | 57 | 177 | 3 | 297 | 24% |
| social-media-platform | Advanced | 125 | 29 | 3 | 377 | 81% |
| chat-application | Intermediate | 35 | 118 | 8 | 375 | 23% |
| project-management-tool | Advanced | 38 | 87 | 0 | 409 | 30% |
| chat-application | Advanced | 48 | 22 | 1 | 460 | 69% |
| chat-application | Beginner | 19 | 44 | 4 | 467 | 30% |