Pith. sign in

← back to paper

Review history

arxiv: 2603.23750 · 2 revisions

IslamicMMLU: A Benchmark for Evaluating LLMs on Islamic Knowledge

  1. 2026-07-14 CONDITIONAL LOW v1.1.0-grok45 novelty 5.0
    19406 ms 6111 in 2431 out 2026-07-14T20:11:49.629333+00:00
  2. 2026-05-15 CONDITIONAL LOW v0.9.0 novelty 7.0
    38762 ms 5506 in 1197 out 2026-05-15T00:03:54.971051+00:00