# HEAL

Source: [HEAL](<https://www.sota2.com/research/dataset/heal>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Benchmarks

Page 1 of 6. This is an index page, not the full collection.

- [Next index page](<https://www.sota2.com/research/dataset/heal.md?page=2>): Follow this link to discover more pages.

- [All-cause mortality prediction on Clalit Health Services (test)](<https://www.sota2.com/research/sota/all-cause-mortality-prediction-on-clalit-health-services-test.md>): All-cause mortality prediction; Clalit Health Services (test).

- [Structural Health Monitoring on SHM vibration-based (5-fold cross-validation)](<https://www.sota2.com/research/sota/structural-health-monitoring-on-shm-vibration-based-5-fold-cross-validation.md>): Structural Health Monitoring; Structural Health Monitoring (SHM) vibration-based (5-fold cross-validation).

- [Classification on National Health and Nutrition Examination Survey Employee 2013–2014 cycle (random sample splits)](<https://www.sota2.com/research/sota/classification-on-national-health-and-nutrition-examination-survey-employee-2013-2014-cycle-random-sample-splits.md>): Classification; National Health and Nutrition Examination Survey Employee 2013–2014 cycle (random sample splits).

- [Activity Recognition on mHealth](<https://www.sota2.com/research/sota/activity-recognition-on-mhealth.md>): Activity Recognition; mHealth.

- [Medical Reasoning on HealthBench Hard](<https://www.sota2.com/research/sota/medical-reasoning-on-healthbench-hard.md>): Medical Reasoning; HealthBench Hard.

- [Jailbreak Attack Safety Evaluation on CARES adversarial mental-health targets 2025](<https://www.sota2.com/research/sota/jailbreak-attack-safety-evaluation-on-cares-adversarial-mental-health-targets-2025.md>): Jailbreak Attack Safety Evaluation; CARES adversarial mental-health targets 2025.

- [Medical Visual Question Answering on MMMU Health & Medicine (test)](<https://www.sota2.com/research/sota/medical-visual-question-answering-on-mmmu-health-and-medicine-test.md>): Medical Visual Question Answering; MMMU Health & Medicine (test).

- [Clinical Question Answering on HealthBench (offline)](<https://www.sota2.com/research/sota/clinical-question-answering-on-healthbench-offline.md>): Clinical Question Answering; HealthBench (offline).

- [Deep Research on HealthBench](<https://www.sota2.com/research/sota/deep-research-on-healthbench.md>): Deep Research; HealthBench.

- [Medical Question Answering on HealthBench Medicine N=5,000 (overall)](<https://www.sota2.com/research/sota/medical-question-answering-on-healthbench-medicine-n-5-000-overall.md>): Medical Question Answering; HealthBench Medicine N=5,000 (overall).

- [Recommendation on Amazon Health](<https://www.sota2.com/research/sota/recommendation-on-amazon-health.md>): Recommendation; Amazon Health.

- [Membership Inference Attack on HealthcareMagic](<https://www.sota2.com/research/sota/membership-inference-attack-on-healthcaremagic.md>): Membership Inference Attack; HealthcareMagic.

- [Medical Reasoning on HealthBench](<https://www.sota2.com/research/sota/medical-reasoning-on-healthbench.md>): Medical Reasoning; HealthBench.

- [Health Evaluation on MMLU-Pro Health (FR) X (test)](<https://www.sota2.com/research/sota/health-evaluation-on-mmlu-pro-health-fr-x-test.md>): Health; MMLU-Pro Health (FR) X (test).

- [Accuracy on MMLU-Pro Health (EN) X (test)](<https://www.sota2.com/research/sota/accuracy-on-mmlu-pro-health-en-x-test.md>): Health; MMLU-Pro Health (EN) X (test).

- [Graph Reasoning on GRBENCH Healthcare](<https://www.sota2.com/research/sota/graph-reasoning-on-grbench-healthcare.md>): Graph Reasoning; GRBENCH Healthcare.

- [Multiclass Classification on Multiclass panel 3 healthcare datasets v1.0 (test)](<https://www.sota2.com/research/sota/multiclass-classification-on-multiclass-panel-3-healthcare-datasets-v1-0-test.md>): Multiclass Classification; Multiclass panel 3 healthcare datasets v1.0 (test).

- [Perturbed Policy Refusal on Health Insurance Portability and Accountability Act (HIPAA)](<https://www.sota2.com/research/sota/perturbed-policy-refusal-on-health-insurance-portability-and-accountability-act-hipaa.md>): Perturbed Policy Refusal; Health Insurance Portability and Accountability Act (HIPAA).

- [Policy Perturbation Detection on Health Insurance Portability and Accountability Act (HIPAA)](<https://www.sota2.com/research/sota/policy-perturbation-detection-on-health-insurance-portability-and-accountability-act-hipaa.md>): Policy Perturbation Detection; Health Insurance Portability and Accountability Act (HIPAA).

- [Binary Classification on binary health datasets avg (test)](<https://www.sota2.com/research/sota/binary-classification-on-binary-health-datasets-avg-test.md>): Binary Classification; binary health datasets avg (test).

- [Medical Question Answering on MMLU-Pro Health](<https://www.sota2.com/research/sota/medical-question-answering-on-mmlu-pro-health.md>): Medical Question Answering; MMLU-Pro Health.

- [Belief assessment on misinformation on MISBELIEF Health domain Hard](<https://www.sota2.com/research/sota/belief-assessment-on-misinformation-on-misbelief-health-domain-hard.md>): Belief assessment on misinformation; MISBELIEF Health domain Hard.

- [Belief assessment on misinformation on MISBELIEF Health domain (Medium)](<https://www.sota2.com/research/sota/belief-assessment-on-misinformation-on-misbelief-health-domain-medium.md>): Belief assessment on misinformation; MISBELIEF Health domain (Medium).

- [Belief assessment on misinformation on MISBELIEF Health domain Easy split](<https://www.sota2.com/research/sota/belief-assessment-on-misinformation-on-misbelief-health-domain-easy-split.md>): Belief assessment on misinformation; MISBELIEF Health domain Easy split.

- [Tabular Classification on Fetal Health](<https://www.sota2.com/research/sota/tabular-classification-on-fetal-health.md>): Tabular Classification; Fetal Health.

- [Question Answering on Biomedical healthcare datasets Avg.](<https://www.sota2.com/research/sota/question-answering-on-biomedical-healthcare-datasets-avg.md>): Question Answering; Biomedical healthcare datasets Avg..

- [Question Answering on LongHealth](<https://www.sota2.com/research/sota/question-answering-on-longhealth.md>): Question Answering; LongHealth.

- [Fact-Checking on PubHealth](<https://www.sota2.com/research/sota/fact-checking-on-pubhealth.md>): Fact-Checking; PubHealth.

- [Health Misinformation Detection on HealthFC](<https://www.sota2.com/research/sota/health-misinformation-detection-on-healthfc.md>): Health misinformation detection; HealthFC.

- [External Data Extraction Attack on HealthcareMagic-101](<https://www.sota2.com/research/sota/external-data-extraction-attack-on-healthcaremagic-101.md>): External Data Extraction Attack; HealthcareMagic-101.

- [Data Extraction Attack on HealthcareMagic-101](<https://www.sota2.com/research/sota/data-extraction-attack-on-healthcaremagic-101.md>): Data Extraction Attack; HealthcareMagic-101.

- [Clinical temporal classification on MHEALTH (test)](<https://www.sota2.com/research/sota/clinical-temporal-classification-on-mhealth-test.md>): Clinical temporal classification; MHEALTH (test).

- [Group Fairness on 8 health datasets aggregated across 4 attributes](<https://www.sota2.com/research/sota/group-fairness-on-8-health-datasets-aggregated-across-4-attributes.md>): Group Fairness; 8 health datasets aggregated across 4 attributes.

- [Regression on Dissecting Health Bias](<https://www.sota2.com/research/sota/regression-on-dissecting-health-bias.md>): Regression; Dissecting Health Bias.

- [Health-related dialogue and decision-making on HealthBench Main](<https://www.sota2.com/research/sota/health-related-dialogue-and-decision-making-on-healthbench-main.md>): Health-related dialogue and decision-making; HealthBench Main.

- [Recommendation on Health (Recall@20, NDCG@20)](<https://www.sota2.com/research/sota/recommendation-on-health-recall-at-20-ndcg-at-20.md>): Recommendation; Health.

- [Blockchain Access Control on Healthcare IoT Simulation](<https://www.sota2.com/research/sota/blockchain-access-control-on-healthcare-iot-simulation.md>): Blockchain Access Control; Healthcare IoT Simulation.

- [Regression on HEALTH (test)](<https://www.sota2.com/research/sota/regression-on-health-test.md>): Regression; HEALTH (test).

- [Classification on HEALTH (test)](<https://www.sota2.com/research/sota/classification-on-health-test.md>): Classification; HEALTH (test).

- [Healthcare Diagnostics on Healthcare Diagnostic Tasks](<https://www.sota2.com/research/sota/healthcare-diagnostics-on-healthcare-diagnostic-tasks.md>): Healthcare Diagnostics; Healthcare Diagnostic Tasks.

- [Deep Research on HealthBench ResearchQA DRB Macro Average](<https://www.sota2.com/research/sota/deep-research-on-healthbench-researchqa-drb-macro-average.md>): Deep Research; HealthBench ResearchQA DRB Macro Average.

- [Fact-checking on HealthVer](<https://www.sota2.com/research/sota/fact-checking-on-healthver.md>): Fact-checking; HealthVer.

- [Multimodal Classification on TimeCAP Weather, Finance, and Healthcare (average)](<https://www.sota2.com/research/sota/multimodal-classification-on-timecap-weather-finance-and-healthcare-average.md>): Multimodal Classification; TimeCAP Weather, Finance, and Healthcare (average).

- [Healthcare Provider Taxonomy Code Classification on Healthcare Taxonomy](<https://www.sota2.com/research/sota/healthcare-provider-taxonomy-code-classification-on-healthcare-taxonomy.md>): Healthcare provider taxonomy code classification; Healthcare Taxonomy.

- [Insight-level Evaluation on SCOpE-QA LLM for Healthcare collection](<https://www.sota2.com/research/sota/insight-level-evaluation-on-scope-qa-llm-for-healthcare-collection.md>): Insight-level Evaluation; SCOpE-QA LLM for Healthcare collection.

- [Insight Generation on Internal document collections non-scientific domain Twitter & Mental Health](<https://www.sota2.com/research/sota/insight-generation-on-internal-document-collections-non-scientific-domain-twitter-and-mental-health.md>): Insight Generation; Internal document collections non-scientific domain Twitter & Mental Health.

- [Insight Generation on Internal document collections - Gut Health Insights non-scientific domain](<https://www.sota2.com/research/sota/insight-generation-on-internal-document-collections-gut-health-insights-non-scientific-domain.md>): Insight Generation; Internal document collections - Gut Health Insights non-scientific domain.

- [Automated Health Data Modeling on AutoHealth Evaluation Benchmark Tasks T1-T17](<https://www.sota2.com/research/sota/automated-health-data-modeling-on-autohealth-evaluation-benchmark-tasks-t1-t17.md>): Automated Health Data Modeling; AutoHealth Evaluation Benchmark Tasks T1-T17.

- [Time Series Classification on Healthcare MT (test)](<https://www.sota2.com/research/sota/time-series-classification-on-healthcare-mt-test.md>): Time Series Classification; Healthcare MT (test).

- [Time Series Classification on Healthcare TP (test)](<https://www.sota2.com/research/sota/time-series-classification-on-healthcare-tp-test.md>): Time Series Classification; Healthcare TP (test).

- [Public Health Specialized Reasoning on GlobalHealthAtlas representative subset (test)](<https://www.sota2.com/research/sota/public-health-specialized-reasoning-on-globalhealthatlas-representative-subset-test.md>): Public Health Specialized Reasoning; GlobalHealthAtlas representative subset (test).

- [Medical Question Answering on HealthBench Hard](<https://www.sota2.com/research/sota/medical-question-answering-on-healthbench-hard.md>): Medical Question Answering; HealthBench Hard.

- [Reward Aggregation on Average HealthBench, WritingBench, PLawBench](<https://www.sota2.com/research/sota/reward-aggregation-on-average-healthbench-writingbench-plawbench.md>): Reward Aggregation; Average HealthBench, WritingBench, PLawBench.

- [Reward Aggregation on HealthBench 500](<https://www.sota2.com/research/sota/reward-aggregation-on-healthbench-500.md>): Reward Aggregation; HealthBench 500.

- [Targeted Attack on HealthcareMagic-101](<https://www.sota2.com/research/sota/targeted-attack-on-healthcaremagic-101.md>): Targeted Attack; HealthcareMagic-101.

- [Untargeted data extraction attack on HealthcareMagic-101](<https://www.sota2.com/research/sota/untargeted-data-extraction-attack-on-healthcaremagic-101.md>): Untargeted data extraction attack; HealthcareMagic-101.

- [Dimensionality Reduction Optimization on Healthy Human Kidney Sex-Based Profiling](<https://www.sota2.com/research/sota/dimensionality-reduction-optimization-on-healthy-human-kidney-sex-based-profiling.md>): Dimensionality Reduction Optimization; Healthy Human Kidney Sex-Based Profiling.

- [Long-horizon agentic task on Healthbench Hard](<https://www.sota2.com/research/sota/long-horizon-agentic-task-on-healthbench-hard.md>): Long-horizon agentic task; Healthbench Hard.

- [Partial Multi-Label Learning on health (Average Precision)](<https://www.sota2.com/research/sota/partial-multi-label-learning-on-health-average-precision.md>): Partial Multi-Label Learning; health.

- [Partial Multi-Label Learning on health (One-error)](<https://www.sota2.com/research/sota/partial-multi-label-learning-on-health-one-error.md>): Partial Multi-Label Learning; health.

- [Partial Multi-Label Learning on health (Hamming Loss)](<https://www.sota2.com/research/sota/partial-multi-label-learning-on-health-hamming-loss.md>): Partial Multi-Label Learning; health.

- [Recommendation on Amazon Health (IID) (Recall@20, NDCG@20)](<https://www.sota2.com/research/sota/recommendation-on-amazon-health-iid-recall-at-20-ndcg-at-20.md>): Recommendation; Amazon Health (IID).

- [Vital signs prediction on BDIMC healthcare datasets](<https://www.sota2.com/research/sota/vital-signs-prediction-on-bdimc-healthcare-datasets.md>): Vital signs prediction; BDIMC healthcare datasets.

- [Medical and Health Knowledge on HealthBench](<https://www.sota2.com/research/sota/medical-and-health-knowledge-on-healthbench.md>): Medical and Health Knowledge; HealthBench.

- [Health Dialogue on HealthBench](<https://www.sota2.com/research/sota/health-dialogue-on-healthbench.md>): Health Dialogue; HealthBench.

- [Multiple Choice Question Answering on Medical and Mental Health MCQA Aggregate (MHQA, MedMCQA, MMLU-hsp, MMLU-pp, USMLE)](<https://www.sota2.com/research/sota/multiple-choice-question-answering-on-medical-and-mental-health-mcqa-aggregate-mhqa-medmcqa-mmlu-hsp-mmlu-pp-usmle.md>): Multiple Choice Question Answering; Medical and Mental Health MCQA (MHQA, MedMCQA, MMLU-hsp, MMLU-pp, USMLE).

- [Mental Health Classification on ANGST, dreaddit, CAMS, and SAD](<https://www.sota2.com/research/sota/mental-health-classification-on-angst-dreaddit-cams-and-sad.md>): Classification; Mental Health Classification Datasets (ANGST, dreaddit, CAMS, SAD).

- [Multiple Choice Question Answering on MMLU ProX Health](<https://www.sota2.com/research/sota/multiple-choice-question-answering-on-mmlu-prox-health.md>): Multiple Choice Question Answering; MMLU ProX Health.

- [Signal Imputation on Wearable Health Data](<https://www.sota2.com/research/sota/signal-imputation-on-wearable-health-data.md>): Signal Imputation; Wearable Health Data.

- [Agentic Task Performance on τ-Telehealth](<https://www.sota2.com/research/sota/agentic-task-performance-on-telehealth.md>): Agentic Task Performance; τ-Telehealth.

- [Mental Health Safety Evaluation on MHSafeEval (v1.0)](<https://www.sota2.com/research/sota/mental-health-safety-evaluation-on-mhsafeeval-v1-0.md>): Mental Health Safety Evaluation; MHSafeEval seven mental-health harm categories 1.0.

- [Medical Question Answering on HealthBench Overall](<https://www.sota2.com/research/sota/medical-question-answering-on-healthbench-overall.md>): Medical Question Answering; HealthBench Overall.

- [Medical Question Answering on HealthBench held-out heart-related n=500 seed 42](<https://www.sota2.com/research/sota/medical-question-answering-on-healthbench-held-out-heart-related-n-500-seed-42.md>): Medical Question Answering; HealthBench held-out heart-related n=500 seed 42.

- [Health Multimodal Evaluation on HealthBench English (test)](<https://www.sota2.com/research/sota/health-multimodal-evaluation-on-healthbench-english-test.md>): Health Multimodal Evaluation; HealthBench English (test).

- [Treatment Planning on HealthBench (treatment-related conversations)](<https://www.sota2.com/research/sota/treatment-planning-on-healthbench-treatment-related-conversations.md>): Treatment planning; HealthBench treatment-related conversations.

- [Bias reduction estimation on Private Healthcare Census Setting](<https://www.sota2.com/research/sota/bias-reduction-estimation-on-private-healthcare-census-setting.md>): Bias reduction estimation; Private Healthcare Census Setting.

- [Medical on HealthBench-500](<https://www.sota2.com/research/sota/medical-on-healthbench-500.md>): Medical; HealthBench-500.

- [Closed-set Question Answering on PubHealth](<https://www.sota2.com/research/sota/closed-set-question-answering-on-pubhealth.md>): Closed-set Question Answering; PubHealth.

- [Time Series Imputation on PhysioNet Challenge 2012 (test)](<https://www.sota2.com/research/sota/time-series-imputation-on-physionet-challenge-2012-test.md>): Time series imputation; PhysioNet Challenge healthcare hourly time series with 48 time steps 2012 (test).

- [Medical Domain Question Answering on HealthBench In-domain, Seen](<https://www.sota2.com/research/sota/medical-domain-question-answering-on-healthbench-in-domain-seen.md>): Medical Domain Question Answering; HealthBench In-domain, Seen.
