| Metric | Value |
|---|---|
| Pusher wins | 742 |
| Supabase wins | 842 |
| Abstains (no tool) | 47 |
| Other tool chosen | 3136 |
| Decisive cases | 1584 |
| Pusher win rate (unweighted) | 46.8% |
| 95% CI | 44.4% - 49.3% |
| Pusher win rate (weighted) | 46.8% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Pusher | Supabase | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek V3.2 | Mid | 14 | 177 | 1 | 51 | 7% |
| MiMo V2 Pro | Frontier | 105 | 26 | 0 | 111 | 80% |
| Claude Sonnet 4.6 | Frontier | 12 | 110 | 0 | 130 | 10% |
| GLM 5 Turbo | Frontier | 110 | 9 | 3 | 121 | 92% |
| Gemini 2.5 Pro | Frontier | 112 | 4 | 0 | 136 | 97% |
| MiniMax M2.7 | Frontier | 14 | 100 | 0 | 127 | 12% |
| Qwen3 Coder Next | Mid | 98 | 12 | 0 | 141 | 89% |
| Mistral Small 4 | Mid | 39 | 49 | 0 | 162 | 44% |
| GPT 5.3 Codex | Frontier | 6 | 74 | 0 | 172 | 8% |
| GPT 5.4 Mini | Mid | 11 | 67 | 2 | 168 | 14% |
| GPT 5.4 | Frontier | 20 | 54 | 0 | 166 | 27% |
| DeepSeek R1 0528 | Frontier | 48 | 17 | 34 | 151 | 74% |
| Claude Opus 4.6 | Frontier | 36 | 28 | 0 | 178 | 56% |
| Llama 4 Scout | Small | 41 | 2 | 1 | 203 | 95% |
| Gemini 2.5 Flash | Small | 18 | 25 | 1 | 199 | 42% |
| Claude Haiku 4.5 | Small | 1 | 38 | 0 | 207 | 3% |
| Kimi K2.5 | Frontier | 8 | 24 | 5 | 204 | 25% |
| Llama 4 Maverick | Frontier | 27 | 1 | 0 | 223 | 96% |
| Devstral 2 2512 | Mid | 8 | 0 | 0 | 244 | 100% |
| MiniMax M3 | Frontier | 4 | 3 | 0 | 2 | 57% |
| DeepSeek V4 Flash | Mid | 2 | 5 | 0 | 2 | 29% |
| DeepSeek V4 Pro | Frontier | 0 | 6 | 0 | 3 | 0% |
| Claude Opus 4.8 | Frontier | 1 | 4 | 0 | 4 | 20% |
| Gemini 3.5 Flash | Small | 4 | 0 | 0 | 5 | 100% |
| GLM 5.2 | Frontier | 2 | 1 | 0 | 6 | 67% |
| MiMo V2.5 Pro | Frontier | 1 | 2 | 0 | 6 | 33% |
| GPT 5.5 | Frontier | 0 | 2 | 0 | 7 | 0% |
| Kimi K2.7 Code | Frontier | 0 | 2 | 0 | 7 | 0% |
| Prompt | Tier | Pusher | Supabase | None | Other | A rate |
|---|---|---|---|---|---|---|
| social-media-platform | Beginner | 101 | 116 | 17 | 195 | 47% |
| social-media-platform | Intermediate | 133 | 75 | 4 | 222 | 64% |
| project-management-tool | Beginner | 64 | 144 | 5 | 224 | 31% |
| project-management-tool | Intermediate | 54 | 138 | 3 | 240 | 28% |
| social-media-platform | Advanced | 112 | 28 | 3 | 294 | 80% |
| chat-application | Intermediate | 17 | 93 | 6 | 320 | 15% |
| project-management-tool | Advanced | 32 | 75 | 0 | 330 | 30% |
| chat-application | Advanced | 45 | 22 | 1 | 366 | 67% |
| chat-application | Beginner | 16 | 36 | 3 | 380 | 31% |
| social-media-platform | Beginner | 33 | 16 | 3 | 43 | 67% |
| project-management-tool | Beginner | 24 | 21 | 2 | 48 | 53% |
| social-media-platform | Intermediate | 28 | 10 | 0 | 57 | 74% |
| project-management-tool | Intermediate | 16 | 21 | 0 | 58 | 43% |
| social-media-platform | Advanced | 28 | 2 | 0 | 64 | 93% |
| chat-application | Beginner | 10 | 19 | 0 | 66 | 34% |
| chat-application | Intermediate | 9 | 16 | 0 | 70 | 36% |
| project-management-tool | Advanced | 7 | 10 | 0 | 77 | 41% |
| chat-application | Advanced | 13 | 0 | 0 | 82 | 100% |