João Pedro Battistella Nadas 84aac0ebfd feat(eval): print per-case + total wall-clock time ...

Useful as prompts grow longer and we benchmark alternate models — bare
PASS/FAIL hides regressions like a prompt that doubles latency without
changing correctness.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-29 15:14:20 +02:00

..

cases

feat: scaffold tolkien v0 — local-LLM classifier wrapper + CLI + eval

2026-05-29 15:09:11 +02:00

run_eval.py

feat(eval): print per-case + total wall-clock time

2026-05-29 15:14:20 +02:00