← back to paper

Review history

arxiv: 2607.01103 · 2 revisions

Clinician-Level Agreement Without Clinical Caution: LLM Evaluator Limits in Medical AI Benchmarking

1. 2026-08-03 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 6.0
   109384 ms 15258 in 10599 out 2026-08-03T01:59:18.270917+00:00
2. 2026-07-02 UNVERDICTED LOW v0.9.1-grok novelty 6.0
   16314 ms 5764 in 1174 out 2026-07-02T12:39:23.982855+00:00