Explore the Coding Agent Index v2.0, with scores by benchmark, Cost per Task and token usage:
https://artificialanalysis.ai/agents/coding-agents
Methodology and version history:
https://artificialanalysis.ai/methodology/coding-agents-benchmarking
FrontierCode v1.1 on Artificial Analysis:
https://artificialanalysis.ai/evaluations/frontiercode
SWE-Atlas-QnA-AA dataset and judge configuration on Hugging Face:
https://huggingface.co/datasets/ArtificialAnalysis/SWE-Atlas-QnA-AA