AA-Omniscience
A knowledge evaluation benchmark released by Artificial Analysis, used to measure the breadth of knowledge of AI models.
Core Facts
Timeline (last 90 days)
In Artificial Analysis's AA-Omniscience benchmark (which penalizes incorrect answers), the top score rose from 4.8 at launch to 46 currently.
Muse Wonder Full scored 30 on the AA-Omniscience factual recall test.
Claude Opus 5.5 scored 46 on the AA-Omniscience factual recall test.
AA-Omniscience is a type of benchmark that evaluates the coverage of a model's factual knowledge, scoring it through a large number of questions requiring precise recall of facts.
On the AA-Omniscience knowledge metric, Muse Wonder scored 25 and Claude Opus 5.5 scored 46.
All Facts (6)
Artificial Analysis是一个独立的AI模型基准测试平台，综合编程能力、数学推理、语言理解、知识问答等多个维度评估模型表现
70%UnverifiedIn Artificial Analysis's AA-Omniscience benchmark (which penalizes incorrect answers), the top score rose from 4.8 at launch to 46 currently.
50%UnverifiedMuse Wonder Full scored 30 on the AA-Omniscience factual recall test.
50%UnverifiedClaude Opus 5.5 scored 46 on the AA-Omniscience factual recall test.
50%UnverifiedAA-Omniscience is a type of benchmark that evaluates the coverage of a model's factual knowledge, scoring it through a large number of questions requiring precise recall of facts.
50%UnverifiedOn the AA-Omniscience knowledge metric, Muse Wonder scored 25 and Claude Opus 5.5 scored 46.
50%