Skip to content
View original post on X: Artificial AnalysisOfficial
Published
38/100

Inkling 2 Small cuts hallucinations to 27% by answering fewer questions

AIArtificial Analysis says Inkling 2 Small's net score on AA-Omniscience v1.1 rises to 16 from -9 for Inkling Small, but it still trails Gemini 3.8 Flash (high, 23) and Claude Sonnet 5.5 (medium, 19). Its hallucination rate falls to 27% from 61%, while its attempt rate drops to 53% from 77% and accuracy rises only to 34% from 32%.
Artificial AnalysisVerified on XOfficial
@ArtificialAnlys
View on X

Part of a thread · earlier post

Inkling 2 Small hallucinates less mainly because it answers fewer questions, while accuracy improves only slightly.

On AA-Omniscience v1.1 its net score improves to 16 from -9 for Inkling Small, but remains behind Gemini 3.8 Flash (high, 23) and Claude Sonnet 5.5 (medium, 19). Its hallucination rate falls to 27% from Inkling Small’s 61%, while its attempt rate falls to 53% from 77% and accuracy rises to 34% from 32%.

Source details

Artificial Analysis · x.comPublished · added here

Original title: Inkling 2 Small hallucinates less mainly because it answers fewer questions, while accuracy improves only slightly.

Topics

Evals & benchmarks