Code Editing on Aider-Polyglot
61.7AccuracyOpenAI-o1-1217
Evaluation Results
| Method | Links | |
|---|---|---|
| OpenAI-o1-12172025.01 | 61.7 | |
| DeepSeek-R1Architecture=MoE, Activated Params=37B, Total Params=671B2025.01 | 53.3 | |
| DeepSeek-V3Architecture=MoE, Activated Params=37B, Total Params=671B2025.01 | 49.6 | |
| Claude-3.5-Sonnet-10222025.01 | 45.3 | |
| OpenAI-o1-mini2025.01 | 32.9 | |
| GPT-4o-05132025.01 | 16 |