Aider Refactoring Benchmark: leaderboard
Aider benchmark for model performance on code refactoring tasks.
Metric: Percent completed correctly (imported). Source: aider.chat. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.5 Sonnet (20241022) | 92.1 | #291 |
| 2 | O1 Preview | 75.3 | #193 |
| 3 | Claude 3 Opus (20240229) | 72.3 | #412 |
| 4 | Claude 3.5 Sonnet (20240620) | 64 | #299 |
| 5 | GPT-4o | 62.9 | #343 |
| 6 | GPT-4 Preview (1106) | 50.6 | #418 |
| 7 | GPT-4o (2024-08-06) | 49.4 | #336 |
| 8 | Gemini 1.5 Pro | 49.4 | #445 |
| 9 | O1 Mini | 44.9 | #323 |
| 10 | GPT-4 Preview (0125) | 33.7 | #486 |
| 11 | DeepSeek V2.5 | 31.5 | #489 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=aider-refactoring-benchmark · How It Works · Data refreshed daily, snapshot 2026-10-20.