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

Biomedical Question Answering research benchmarks · SOTA2 Research

Biomedical Question Answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

77Attack Accuracy

40

Apr 28, 2026

Nemotron-CC_ASI

68.32Accuracy

13

Apr 1, 2026

LLAMA-70B+7B (PT)

29Factoid Acc

11

May 22, 2026

PubMedQA PQA-L In-Domain (test)

78Accuracy

11

Feb 26, 2026

MedMCQA In-Domain (test)

90Accuracy

10

Feb 26, 2026

54.8ROUGE

8

Apr 14, 2026

BioMRC TINY Setting A (test)

AOA-READER WITH BIOBERT EMBEDDING

93.33Accuracy

8

Feb 26, 2026

BioACE human-assessed TREC BioGen 2025

hltcoe-multiagt

96.41Nugget Precision

7

Mar 19, 2026

BioMRC LITE Setting A (test)

AOA-READER WITH BIOBERT EMBEDDING

86.74Accuracy

7

Feb 26, 2026

BioMRC LITE Setting A (dev)

AOA-READER WITH BIOBERT EMBEDDING

87.22Accuracy

7

Feb 26, 2026

PaperSearchQA (test)

42.6Bio Score

6

Jun 18, 2026

BioACE automatic evaluation N=50 runs

agent_faiss_deepseek

94.96Precision

6

Mar 19, 2026

Four biomedical QA datasets macro-averaged (test)

Med42-Llama3-8B

85.3Faithfulness

4

Feb 26, 2026

0.6Baseline Accuracy

2

Jun 2, 2026

PubMedQA (test)

0.254CUS

2

Apr 1, 2026

42.1CUS

2

Apr 1, 2026

—

—Primary metric

0

May 22, 2026

—

—Primary metric

0

May 22, 2026

—

—Primary metric

0

May 22, 2026

—

—Primary metric

0

May 22, 2026

Popular datasets

PubMedQA BioMRC BioASQ BioACE MMLU

Follow for updates

Join SOTA2 Contact