Evidence / original sources

A claim should lead somewhere.

Follow the references behind Clinical Benchmark. Each entry explains its role, links to the original publication, and identifies the guides that use it.

Content updated September 28, 2026. Inclusion does not imply endorsement.

03

Ankit Pal, Logesh Kumar Umapathi and Malaikannan Sankarasubbu

MedMCQA: A Large-scale Multi-Subject Multi-Choice Dataset ↗

Original exam-based construction, exact split statistics and retrieval comparison.

Version: CHIL 2022 · 2022-04-07

Evidence locator: Sections 2–3; Tables 2 and 4

proceedings.mlr.press