davidkling/hf-coding-tools-dashboard

HuggingFace AI编码工具仪表板的基准数据，用于跟踪AI编码工具（Claude Code、Codex、Copilot、Cursor）在32个开发者类别中推荐HuggingFace产品的情况。数据集包含四个部分：results（完整的基准测试结果，包括LLM响应、成本、令牌、延迟和产品检测）、queries（跨32个类别的基准查询定义）、runs（运行元数据和工具/模型配置）和products（带有检测关键词的HuggingFace产品目录）。

Benchmark data from the HuggingFace AI Dashboard — tracking how AI coding tools (Claude Code, Codex, Copilot, Cursor) recommend HuggingFace products across 32 developer categories. The dataset includes four parts: results (full benchmark results with LLM responses, cost, tokens, latency, and product detection), queries (benchmark query definitions across 32 categories), runs (run metadata and tool/model configurations), and products (HuggingFace product catalog with detection keywords).