| Metric | Value |
|---|---|
| Pusher wins | 684 |
| Supabase wins | 906 |
| Abstains (no tool) | 54 |
| Other tool chosen | 3151 |
| Decisive cases | 1590 |
| 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 | 9 | 152 | 1 | 36 | 6% |
| Claude Sonnet 4.6 | Frontier | 7 | 113 | 0 | 132 | 6% |
| Qwen3 Coder Next | Mid | 100 | 11 | 0 | 139 | 90% |
| MiMo V2 Pro | Frontier | 84 | 23 | 0 | 90 | 79% |
| Gemini 2.5 Pro | Frontier | 105 | 1 | 0 | 146 | 99% |
| MiniMax M2.7 | Frontier | 11 | 86 | 0 | 99 | 11% |
| GLM 5 Turbo | Frontier | 76 | 9 | 3 | 110 | 89% |
| Mistral Small 4 | Mid | 34 | 51 | 0 | 162 | 40% |
| GPT 5.4 Mini | Mid | 8 | 71 | 4 | 165 | 10% |
| GPT 5.3 Codex | Frontier | 6 | 70 | 0 | 176 | 8% |
| DeepSeek R1 0528 | Frontier | 45 | 17 | 40 | 149 | 73% |
| Claude Opus 4.6 | Frontier | 31 | 28 | 0 | 138 | 53% |
| GPT 5.4 | Frontier | 15 | 39 | 0 | 141 | 28% |
| Claude Haiku 4.5 | Small | 1 | 47 | 0 | 197 | 2% |
| Llama 4 Scout | Small | 40 | 4 | 0 | 204 | 91% |
| DeepSeek V4 Flash | Mid | 10 | 27 | 0 | 15 | 27% |
| MiniMax M3 | Frontier | 13 | 19 | 0 | 22 | 41% |
| Gemini 2.5 Flash | Small | 7 | 25 | 0 | 166 | 22% |
| Claude Opus 4.8 | Frontier | 6 | 25 | 0 | 23 | 19% |
| Llama 4 Maverick | Frontier | 26 | 1 | 0 | 222 | 96% |
| MiMo V2.5 Pro | Frontier | 13 | 12 | 0 | 29 | 52% |
| Gemini 3.5 Flash | Small | 20 | 4 | 0 | 30 | 83% |
| DeepSeek V4 Pro | Frontier | 2 | 20 | 1 | 30 | 9% |
| Kimi K2.5 | Frontier | 3 | 18 | 5 | 170 | 14% |
| GLM 5.2 | Frontier | 9 | 7 | 0 | 38 | 56% |
| Kimi K2.7 Code | Frontier | 1 | 14 | 0 | 39 | 7% |
| GPT 5.5 | Frontier | 0 | 12 | 0 | 42 | 0% |
| Devstral 2 2512 | Mid | 2 | 0 | 0 | 241 | 100% |
| Prompt | Tier | Pusher | Supabase | None | Other | A rate |
|---|---|---|---|---|---|---|
| social-media-platform | Beginner | 119 | 144 | 22 | 242 | 45% |
| project-management-tool | Beginner | 78 | 185 | 7 | 265 | 30% |
| social-media-platform | Intermediate | 162 | 95 | 5 | 269 | 63% |
| project-management-tool | Intermediate | 57 | 176 | 3 | 298 | 24% |
| social-media-platform | Advanced | 126 | 30 | 4 | 373 | 81% |
| chat-application | Intermediate | 31 | 119 | 8 | 377 | 21% |
| project-management-tool | Advanced | 38 | 90 | 0 | 406 | 30% |
| chat-application | Advanced | 52 | 23 | 1 | 456 | 69% |
| chat-application | Beginner | 21 | 44 | 4 | 465 | 32% |