Categoryexternal
MeasureAbstention rate on missed questions
DifficultyKnowledge questions with an abstain option
AA-Omniscience-Decision non-hallucination rate is one component of the Artificial Analysis Decision Index v1.0, run by Artificial Analysis. It is the share of questions not answered correctly where the model chose "I don't know" instead of a wrong answer. Higher is better.
AA-Omniscience-Decision non-hallucination rate ranking
13 models with a published AA-Omniscience-Decision non-hallucination rate value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
Models ranked by their published AA-Omniscience-Decision non-hallucination rate value| Rank | Model | Provider | Abstention rate on missed questions |
|---|
| 1 | BAelephant-1 | Baseten | 93.2 |
| 2 |  d1-ultra | Liquid AI | 84.5 |
| 3 |  Microsoft-Decision-1 | Microsoft | 39.8 |
About AA-Omniscience-Decision non-hallucination rate
What the benchmark measures and how its value is published, from the source’s own record.
What is AA-Omniscience-Decision non-hallucination rate?
AA-Omniscience-Decision non-hallucination rate is an external benchmark published by Artificial Analysis Decision Index v1.0. AA-Omniscience-Decision non-hallucination rate is one component of the Artificial Analysis Decision Index v1.0, run by Artificial Analysis. It is the share of questions not answered correctly where the model chose "I don't know" instead of a wrong answer. Higher is better. The source rates its difficulty as knowledge questions with an abstain option.
How is AA-Omniscience-Decision non-hallucination rate scored?
Each model's result is published by Artificial Analysis Decision Index v1.0 as abstention rate on missed questions. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 13 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
ModelScale
