Alvis
|
54cb940279
|
Update docs: add benchmarks/ section, fix complex tier description
- CLAUDE.md: add benchmark commands (run_benchmark.py flags, dry-run,
categories, voice benchmark)
- README.md: add benchmarks/ to Files tree; fix incorrect claim that
complex tier requires /think prefix — it is auto-classified via regex
and embedding similarity; fix "Complex agent (/think prefix)" heading
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-03-24 02:13:14 +00:00 |
|