Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Clinical Question Answering research benchmarks · SOTA2 Research

Clinical Question Answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

MedXpertQA Multimodal modality (offline)

54.73Accuracy

38

Jun 9, 2026

LiveClin Multimodal (offline)

74.59Accuracy

38

Jun 9, 2026

LiveMedBench (offline)

57.95Accuracy

38

Jun 9, 2026

HealthBench (offline)

31.79Accuracy

38

Jun 9, 2026

MedXpertQA Text modality (offline)

46.49Accuracy

38

Jun 9, 2026

LiveClin Text modality (offline)

92.08Accuracy

38

Jun 9, 2026

94.2Accuracy

30

Jul 3, 2026

92.6Accuracy

14

Feb 26, 2026

86.7Accuracy

14

Feb 26, 2026

86.1Accuracy

14

Feb 26, 2026

ArchEHR-QA 2026 (test)

13ST1

8

May 12, 2026

Openthinker 32B

1.24CCor

7

May 13, 2026

MedQA-open (test)

1.32CCor

7

May 13, 2026

81.28Accuracy

7

Feb 26, 2026

ESAP endocrinology examination 2025 (test)

91.2Diagnosis Accuracy

4

Feb 26, 2026

HealthBench Hard Set

0.386Overall Score

2

Mar 24, 2026

Popular datasets

MedQA HealthBench MedXpertQA LiveClin GPQA

Follow for updates

Join SOTA2 Contact