Repo

persian-llm-eval

Persian LLM benchmark and eval harness — 300 items across 10 tracks, 23 frontier model runs, deterministic scoring with bootstrap confidence intervals, and a leaderboard. Iranian Persian / Farsi.

Visit github.com ↗

Built with

Pythonbenchmarkdatasetevaluationfarsiiran

Comments · 0

No comments yet. Tried it? Tell Parsa what worked, what didn't, or what you'd want next.

More from members

All projects

See what other members are building and what each project is looking for.