Skip to content

Add RULER and full LongBench benchmark suite #4

@jagmarques

Description

@jagmarques

Current evaluation uses perplexity on multi-topic passages and 5 custom QA tasks. For paper and production credibility, need full RULER (needle-in-a-haystack, multi-hop) and LongBench (16 tasks across summarization, QA, few-shot, code completion). Preliminary LongBench results show task-dependent quality — narrative QA degrades +8-11% at 10x while factual trivia improves.

Metadata

Metadata

Assignees

No one assigned

    Labels

    benchmarksBenchmark evaluationenhancementNew feature or request

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions