Environments

MainframeFaithful emulation of batch and online mainframe systems.EnterpriseSWE
GoProduction Go services with their tickets and tests, run in containers.EnterpriseSWE
FigmaA headless Figma runtime with the Plugin API and MCP tools.LH-Bench
Financial document reasoningBank statements and filings as PDFs, every transaction labelled by risk analysts.LH-Bench
Content generationProgrammatic video from source documents, judged by expert educators.LH-Bench

Datasets

Agent trajectoriesEvery action, verdict and verifier output from the benchmark runs.