← Back to the wire

Baseten Releases Bison-1 and Groundhog-1, Topping Decision Model Index

AchievementModelNov 21, 2026

Baseten's bison-1 scores 76 on the Artificial Analysis Decision Index v2.1, ranking first of 19 models and one point above Liquid AI's d1.2-ultra. Baseten released bison-1 and groundhog-1, open-weight decision models built on Google's Gemma 4 that return calibrated probabilities instead of text. bison-1 is a 31B dense model; groundhog-1 is a 26B MoE with about 4B active parameters. Both accept 128k tokens and images, and BF16 weights are available on Hugging Face. All figures are self-reported.

Receipt № 30141 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

01med
www.marktechpost.comBloghttps://www.marktechpost.com/2026/11/20/baseten-bison-1-groundhog-1-gemma-4-decision-models/This source details the full component benchmark breakdown for Bison-1, its soft-label training rationale, and deployment specifics like identical APIs and open BF16 weights on Hugging Face.
PRIMARY
GoogleCompanyGemma 4ModelHugging FaceCompanyGemma 4 31BModelArtificial AnalysisCompanyLiquid AICompanyBasetenCompanyBison-1ModelGroundhog-1ModelGemma 4 26B-A4BModeld1.2-ultraModel
Canonical: https://www.marktechpost.com/2026/11/20/baseten-bison-1-groundhog-1-gemma-4-decision-models/