List your company

Code Editing on EditBench Core set

66.67Pass@1Claude Sonnet 4
16.59429.594542.59555.5955Mar 13, 2026

Evaluation results

MethodLinks
Claude Sonnet 4Model Weight Type=Closed Weight2026.0366.67
GPT o4-miniModel Weight Type=Closed Weight2026.0357.41
SEMREP QwQ-32BModel Weight Type=Open Weight, Model Size=32B2026.0357.41
Qwen3-CoderModel Weight Type=Open Weight, Model Size=405B2026.0355.56
GLM-4.6Model Weight Type=Open Weight, Model Size=355B2026.0355.56
Gemini 2.5 ProModel Weight Type=Closed Weight2026.0354.63
Finetuned QwQ-32BModel Weight Type=Open Weight, Model Size=32B2026.0353.7
Qwen2.5-72B-InstructModel Weight Type=Open Weight, Model Size=72B2026.0353.7
QwQ-32BModel Weight Type=Open Weight, Model Size=32B2026.0350.93
SEMREP Qwen2.5-Coder-7BModel Weight Type=Open Weight, Model Size=7B2026.0332.41
gemma-3-12b-itModel Weight Type=Open Weight, Model Size=12B2026.0323.15
Finetuned Qwen2.5-Coder-7BModel Weight Type=Open Weight, Model Size=7B2026.0323.15
Qwen2.5-Coder-7BModel Weight Type=Open Weight, Model Size=7B2026.0318.52