LLM Bench Marker

A benchmarking tool that runs multi‑model sweeps on curated datasets with fixed prompts to identify the best cost/quality trade‑offs.

It logs tokens, latency, and quality scores per run, compares models side‑by‑side, and highlights the most suitable option for a target budget or score.

Includes run versioning and exportable reports (CSV/JSON) for analysis and sharing.