 Profa
|
e2180f83e7
|
docs: add Code Intelligence token reduction benchmark results
Benchmark shows 79.9% input token reduction and 92% context relevance
with Code Intelligence vs baseline approach.
Key findings:
- 1,671 → 336 input tokens per query
- 6 files → 2 semantic chunks
- 35% → 92% relevance score
- ~$15/month savings at 100 queries/day
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
|
2025-12-22 16:07:05 +00:00 |
|