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>

CLAUDE.md

@@ -18,8 +18,24 @@ python3 test_routing.py [--easy-only|--medium-only|--hard-only]
 
 # Use case tests — read the .md file and follow its steps as Claude Code
 # example: read tests/use_cases/weather_now.md and execute it
+
+# Routing benchmark — measures tier classification accuracy across 120 queries
+# Run from benchmarks/ — Adolf must be running. DO NOT run during active use (holds GPU).
+cd benchmarks
+python3 run_benchmark.py                       # full run (120 queries)
+python3 run_benchmark.py --tier light          # light tier only (30 queries)
+python3 run_benchmark.py --tier medium         # medium tier only (50 queries)
+python3 run_benchmark.py --tier complex --dry-run  # complex tier, medium model (no API cost)
+python3 run_benchmark.py --category smart_home_control
+python3 run_benchmark.py --ids 1,2,3
+python3 run_benchmark.py --list-categories
+
+# Voice benchmark
+python3 run_voice_benchmark.py
+
+# benchmark.json (dataset) and results_latest.json are gitignored — not committed
 ```
 
 ## Architecture
 
-@ARCHITECTURE.md
+@README.md