benchmark-data

Benchmark the performances of various Swift layout frameworks (autolayout, UIStackView, PinLayout, LayoutKit, FlexLayout, Yoga, ...)

Benchmark data (i.e., DeepMind Control Suite and MuJoCo) for RL.

Curated, traceable snapshots of public math reasoning datasets. Canonical JSONL format with provenance tracking — plug directly into math-eval.

Open evidence archive for local-LLM measurements: 75 sealed run bundles from AMD Strix Halo (gfx1151) and DGX Spark — per-request records, manifests, checksums, and the claim catalog behind agmind.ai. CC BY 4.0

Large benchmark data for 4kills/go-zlib and 4kills/go-libdeflate, removed from the original go library/repository itself to minimize library size.

Research datasets and experimental results from comprehensive ML benchmarking on AMD MI300X hardware. Contains raw telemetry, processed metrics, and reproducible analysis artifacts from both inference and training workloads, supporting research and comparative studies.

Versioned sealed data pack for the suite's AITA social-sycophancy benchmark.