BhagyasriUddandam/evallint

Audits LLM eval datasets for the flaws that make evaluations silently lie — discrimination failure, near-duplicates, class imbalance.

2 best points · 0 comments · 1 Hacker News post · 1 GitHub stars · View on GitHub

Hacker News discussions

• GSM8K problems can't tell Haiku 4.5 from Opus 5 (2 points, 0 comments, by Bhagichan, 2026-08-24)