turnframe-eval 0.1.0

Model evaluation harness for Turnframe: corpora, samples, deterministic assertions and judge votes
Documentation
1
2
3
4
5
# Baselines

Reports of live runs of `tests/live_corpus`, one file per run, compared against later runs
with `turnframe_eval::baseline::compare`. How each was run and what it cost is in
`docs/benchmarks.md`.