all the models — AI benchmark observatory
← Benchmarks

AA-Omniscience Index

AA-Omniscience Index is Artificial Analysis's knowledge-reliability metric. It rewards correct answers, penalizes hallucinations, and does not penalize abstention. Scores range from -100 to 100, where 0 means as many correct as incorrect answers.

id aa-omniscience-index · max 200 · 3 models reported

#ModelScore
1Grok 4.5
xAI
126.00
2Inkling
Thinking Machines Lab · open
2.10
AA-Omniscience Index Leaderboard · all the models