YidiDev/jev-benchmark

Rubric-Based Zero-Shot Classification Benchmark: Jev vs Claude Haiku 4.5 vs Claude Sonnet 5 vs OpenJev on rubric-conditioned classification, chained decision execution, and exam grading -- with full price tracking.

2 best points · 1 comments · 1 Hacker News post · 3 GitHub stars · View on GitHub

Hacker News discussions

• Jev deserves hype but not the type its getting (2 points, 1 comments, by yididev, 2026-09-23)