Healthcare & Medical Index
Assesses model performance across the healthcare and medical domain. Capabilities evaluated include domain-specific knowledge (medicine, public health, biomedical sciences), clinical diagnosis and assessment, reasoning over long patient records and claims files, patient documentation, medication management, and more.
Ver flujos de trabajo representativosThe Artificial Analysis Healthcare & Medical Index combines performance across benchmarks chosen for clinical and healthcare-support work, spanning medical knowledge, clinical reasoning, long-context reasoning over patient records, agentic workflows, and non-hallucination. We map common tasks from O*NET occupational classifications, then select benchmarks that represent this real-world work. Weights are derived from how often capabilities appear across those tasks.
This composite metric provides a single score for tracking model performance across healthcare tasks. Artificial Analysis ejecuta de forma independiente todas las evaluaciones subyacentes. Consulta nuestra metodología de Benchmarking de Inteligencia para saber cómo se realizan las evaluaciones.
| Capacidad | Peso | Evaluaciones |
|---|---|---|
| Medical & Health Knowledge | 30 % | AA-Omniscience Health Accuracy |
| Agentic Knowledge Work | 25 % | GDPval-AA v2 |
| Long-Context Reasoning | 15 % | MLCR-AA |
| Non-Hallucination | 10 % | AA-Omniscience Non-Hallucination |
| Reasoning | 10 % | HLE |
| Agentic Customer Interaction | 10 % | 𝜏³-Banking |
Puntuación
Artificial Analysis Healthcare & Medical Index
Artificial Analysis Healthcare & Medical Index: desglose de capacidades
Desglose de capacidades
Artificial Analysis Healthcare & Medical Index: Medical & Health Knowledge
Flujos de trabajo representativos
Flujos de trabajo reales que ponen a prueba las capacidades a las que Healthcare & Medical Index da mayor peso.
Ejemplo: Reassess a returning patient with worsening symptoms against the original EHR workup to build a differential from the new labs and imaging and surface alternative diagnoses the findings point to.
Ejemplo: A surgical team that encounters unexpected anatomy mid-laparoscopic-procedure. Retrieve comparable case reports and imaging precedents and quickly output findings relevant to their immediate decision.
Ejemplo: Turn a clinician's dictated notes from a follow-up visit into a structured SOAP note, pulling the patient's active problems and relevant history from the existing chart, placing each finding in the right section, and flagging the gaps the next provider would need filled.
Ejemplo: Calculate a child's per-dose amount from their measurements and the prescriber's notes against the available suspension concentration, convert it to the millilitres to measure at each dose, and produce caregiver instructions that keep the total within the safe daily range.
Ejemplo: Evaluate whether a dermatology team should adopt a newer procedure backed by emerging but limited long-term evidence to summarise the published trials and safety data, compare outcomes against the current standard of care, and outline the open questions the team still needs to resolve.
Ejemplo: Work a several-hundred-page medical record assembled from multiple providers to reconstruct the treatment timeline, identify which encounters relate to the injury in question, and answer reviewer questions with citations to the underlying documents.
Ejemplo: Turn a patient's after-visit summary into plain-language, step-by-step home-care instructions in their preferred language, anticipate the questions they are most likely to ask, and confirm the follow-up appointment and how to reach the clinic with concerns.
Fecha de lanzamiento
Artificial Analysis Healthcare & Medical Index vs. fecha de lanzamiento
Costo
Artificial Analysis Healthcare & Medical Index: costo por tarea
Artificial Analysis Healthcare & Medical Index: costo total
Velocidad
Artificial Analysis Healthcare & Medical Index: tiempo por tarea
Tokens de salida
Artificial Analysis Healthcare & Medical Index: tokens de salida por tarea
Preguntas frecuentes
Según el Healthcare & Medical Index de Artificial Analysis, los modelos de IA con mejor desempeño en trabajos de salud y medicina son actualmente Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) (56), Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) (52) y Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) (52). La clasificación se actualiza a medida que se lanzan nuevos modelos.
Sí. El Healthcare & Medical Index de Artificial Analysis es un benchmark independiente que mide el desempeño de los modelos de IA en trabajos de salud y medicina. Evalúa conocimientos y razonamiento clínicos, razonamiento con historiales extensos de pacientes, flujos de trabajo agénticos y ausencia de alucinaciones.
El Healthcare & Medical Index es un benchmark compuesto de Artificial Analysis que evalúa el desempeño de los modelos en salud y medicina. Las capacidades evaluadas incluyen conocimientos específicos (medicina, salud pública y ciencias biomédicas), diagnóstico y evaluación clínica, razonamiento sobre historiales extensos y expedientes de reclamaciones, documentación de pacientes, gestión de medicamentos y más.
El Healthcare & Medical Index se calcula como el promedio ponderado de las puntuaciones de sus capacidades. Estas son las puntuaciones y sus pesos: Medical & Health Knowledge (30 %), Agentic Knowledge Work (25 %), Long-Context Reasoning (15 %), Non-Hallucination (10 %), Reasoning (10 %) y Agentic Customer Interaction (10 %).
El Healthcare & Medical Index incluye AA-Omniscience Health Accuracy, GDPval-AA v2, MLCR-AA, AA-Omniscience Non-Hallucination, HLE y 𝜏³-Banking.
Actualmente, Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) tiene la puntuación más alta en el Healthcare & Medical Index: 56 entre los modelos con resultados publicados. Ver modelo
Una puntuación más alta en el Healthcare & Medical Index indica un mejor desempeño general en los benchmarks que componen el índice. Para un caso de uso específico, los resultados de cada benchmark pueden ser más informativos que la puntuación compuesta.