| Metric | Value |
|---|---|
| Merge wins | 292 |
| Next.js wins | 353 |
| Abstains (no tool) | 879 |
| Other tool chosen | 5004 |
| Decisive cases | 645 |
| Merge win rate (unweighted) | 45.3% |
| 95% CI | 41.5% - 49.1% |
| Merge win rate (weighted) | 45.3% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Merge | Next.js | None | Other | A rate |
|---|---|---|---|---|---|---|
| Gemini 2.5 Pro | Frontier | 36 | 30 | 29 | 257 | 55% |
| GPT 5.3 Codex | Frontier | 34 | 18 | 16 | 284 | 65% |
| Claude Sonnet 4.6 | Frontier | 30 | 22 | 13 | 285 | 58% |
| Kimi K2.5 | Frontier | 48 | 3 | 36 | 161 | 94% |
| Claude Haiku 4.5 | Small | 0 | 41 | 18 | 270 | 0% |
| GPT 5.4 | Frontier | 21 | 18 | 23 | 196 | 54% |
| DeepSeek V3.2 | Mid | 0 | 38 | 28 | 191 | 0% |
| Claude Opus 4.6 | Frontier | 0 | 34 | 13 | 216 | 0% |
| MiMo V2 Pro | Frontier | 14 | 15 | 26 | 208 | 48% |
| GLM 5 Turbo | Frontier | 27 | 1 | 148 | 87 | 96% |
| MiniMax M2.7 | Frontier | 1 | 26 | 28 | 191 | 4% |
| DeepSeek R1 0528 | Frontier | 2 | 22 | 82 | 246 | 8% |
| GPT 5.5 | Frontier | 9 | 13 | 9 | 57 | 41% |
| GPT 5.4 Mini | Mid | 3 | 19 | 17 | 269 | 14% |
| Gemini 3.5 Flash | Small | 15 | 3 | 30 | 39 | 83% |
| Mistral Small 4 | Mid | 0 | 18 | 11 | 290 | 0% |
| MiniMax M3 | Frontier | 13 | 1 | 12 | 62 | 93% |
| MiMo V2.5 Pro | Frontier | 7 | 5 | 9 | 68 | 58% |
| Kimi K2.7 Code | Frontier | 9 | 1 | 10 | 69 | 90% |
| DeepSeek V4 Pro | Frontier | 7 | 2 | 26 | 50 | 78% |
| Devstral 2 2512 | Mid | 2 | 7 | 51 | 269 | 22% |
| Claude Opus 4.8 | Frontier | 7 | 1 | 30 | 50 | 88% |
| GLM 5.2 | Frontier | 5 | 1 | 9 | 75 | 83% |
| DeepSeek V4 Flash | Mid | 2 | 3 | 13 | 64 | 40% |
| Llama 4 Maverick | Frontier | 0 | 4 | 16 | 323 | 0% |
| Llama 4 Scout | Small | 0 | 4 | 26 | 290 | 0% |
| Qwen3 Coder Next | Mid | 0 | 3 | 112 | 217 | 0% |
| Gemini 2.5 Flash | Small | 0 | 0 | 38 | 220 | n/a |
| Prompt | Tier | Merge | Next.js | None | Other | A rate |
|---|---|---|---|---|---|---|
| url-shortener | Beginner | 0 | 183 | 125 | 217 | 0% |
| ai-revenue-ops-copilot | Beginner | 159 | 0 | 27 | 306 | 100% |
| ai-revenue-ops-copilot | Intermediate | 87 | 0 | 96 | 324 | 100% |
| url-shortener | Intermediate | 0 | 64 | 94 | 362 | 0% |
| weather-dashboard | Advanced | 0 | 49 | 6 | 461 | 0% |
| ai-revenue-ops-copilot | Advanced | 45 | 0 | 92 | 369 | 100% |
| multi-tenant-crm | Beginner | 0 | 24 | 145 | 355 | 0% |
| weather-dashboard | Intermediate | 0 | 14 | 1 | 518 | 0% |
| full-stack-web-app | Beginner | 0 | 7 | 63 | 47 | 0% |
| multi-tenant-crm | Intermediate | 1 | 5 | 114 | 394 | 17% |
| full-stack-web-app | Intermediate | 0 | 4 | 28 | 61 | 0% |
| full-stack-web-app | Advanced | 0 | 2 | 8 | 84 | 0% |
| multi-tenant-crm | Advanced | 0 | 1 | 36 | 493 | 0% |
| url-shortener | Advanced | 0 | 0 | 44 | 477 | n/a |
| weather-dashboard | Beginner | 0 | 0 | 0 | 536 | n/a |