Google's grounded question-answering model for producing answers tied to supplied source passages, with answerability scoring in the response flow.
---
Quality Score
---
Arena ELO
Undisclosed
Parameters
7K
Context
Use this section to answer one simple question first: how much outside evidence do we have that this model performs well? Structured benchmark scores appear first, then official provider evidence, then live arena signal.
This model category does not have a stable public benchmark standard we trust enough to present as comparable benchmark coverage.
A full normalized benchmark row is not available for this model yet.
This usually means public benchmark sources have not published stable data for this release yet.
Sign in to join the discussion
0
Downloads
0
Likes
Dec 2023
Released