Artificial Analysis reports Inkling 2 Small benchmark results
Article timeline
The articles in this story. Times are ET.
Artificial AnalysisOfficialInkling 2 Small cuts hallucinations to 27% by answering fewer questionsAIArtificial 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 AnalysisOfficialPickArtificial Analysis reports Inkling 2 Small's AA-Briefcase benchmark scores
AIArtificial Analysis says Inkling 2 Small scores 1527 Elo on AA-Briefcase, versus 912 for Inkling Small, 1439 for Claude Sonnet 5.5 (medium), and 1203 for Gemini 3.8 Flash (high). AA-Briefcase tests long-horizon business workflows that require spreadsheets, presentations, and memos. Inkling 2 Small passes 50% of rubric checks, compared with 20% for Inkling Small, and scores 1634 Elo on analytical quality and 1564 Elo on presentation.
- Artificial AnalysisOfficialInkling 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 AnalysisOfficialPickArtificial Analysis reports Inkling 2 Small scores 1527 Elo on AA-Briefcase
AIArtificial Analysis reports that Inkling 2 Small scores 1527 Elo on AA-Briefcase, a benchmark of long-horizon business workflows such as spreadsheets, presentations, and memos. That is 615 points above Inkling Small at 912 Elo, and ahead of Claude Sonnet 5.5 (medium) at 1439 and Gemini 3.8 Flash (high) at 1203. It passes 50% of rubric checks versus 20% for Inkling Small.
