Índices de capacidades

Finance & Accounting Index

Measures performance on the finance and accounting domain, including financial knowledge, mathematical reasoning, long-context analysis, reporting, and more.

AA-OmniscienceGDPval-AA v2Humanity's Last ExamAA-LCR v1.1𝜏³-Banking

Strategy & Ops Index

Measures performance on the strategy and operations domain, including business knowledge, agentic workflows, and customer interaction.

AA-OmniscienceGDPval-AA v2𝜏³-BankingAA-LCR v1.1

Legal Index

Measures performance on the legal domain, including legal knowledge, document analysis, long-context reasoning, and non-hallucination.

AA-OmniscienceGDPval-AA v2AA-LCR v1.1𝜏³-BankingHumanity's Last Exam

Healthcare & Medical Index

Measures performance on the medical and healthcare domain, including clinical knowledge, clinical reasoning, long-context reasoning over patient records, agentic workflows, and non-hallucination.

AA-OmniscienceGDPval-AA v2𝜏³-BankingHumanity's Last ExamMLCR-AA

Engineering Index

Measures performance on the engineering domain, including engineering knowledge, quantitative reasoning, agentic execution, and terminal use.

AA-OmniscienceHumanity's Last ExamGPQA DiamondCritPtGDPval-AA v2Terminal-Bench v2.1

Economics Index

Measures performance on the economics domain, including economics knowledge, quantitative reasoning, agentic execution, and long-context analysis.

AA-OmniscienceGDPval-AA v2Humanity's Last ExamAA-LCR v1.1