เบนช์มาร์ก

benchmarks

ผลจาก benchmark suite

Token reduction

54.12%

balanced mode, benchmark suite

Character reduction

58.23%

balanced mode, benchmark suite

Line reduction

66.67%

fixed benchmark fixtures

Warning preservation

100%

heuristic checks; review critical output

Benchmark ใช้ fixed baseline และ Noyap-mode responses. Token count ใช้ gpt-tokenizer และตรวจ required technical terms, warnings, Thai quality, English quality แบบ heuristic จึงยังควร review เคสสำคัญด้วยคน.

measured

สิ่งที่ benchmark วัด

✔ token reduction

✔ character reduction

✔ line reduction

✔ meaning preservation

✔ warning preservation

✔ required technical terms

✔ Thai and English quality checks

✔ manual review checklist

repo files

ไฟล์ benchmark ใน GitHub

github

summary.md  https://github.com/ppwnr88/noyap/blob/main/benchmarks/results/summary.md
results.json https://github.com/ppwnr88/noyap/blob/main/benchmarks/results/results.json
cases.json   https://github.com/ppwnr88/noyap/blob/main/benchmarks/cases.json
methodology  https://github.com/ppwnr88/noyap/blob/main/benchmarks/README.md

summary.md results.json cases.json methodology