Code / benchmarks/promptsets/README.md

benchmarks/promptsets/README.md 18 lines
---
project: modelmap
document: Prompt sets index
author: Simon-Pierre Boucher
contact: contact@spboucher.ai
website: https://modelmap.io
created: 2026-08-12
status: draft
---

# Mapping prompt corpora

Versioned artifacts with checksums (charter §0.3). Planned corpora: code,
math, French, English, factual recall, reasoning, chat. Each corpus ships as
a checksummed JSONL file plus a manifest recording its version and origin.

*(No corpora committed yet — designed during Phase 5.)*