Sign in
Pending benchmarksTracking since Nov 20, 2026

Is groundhog-1 state of the art?Pending benchmarks.Announced Nov 20, 2026; no independent results yet.

Base Labs' mixture-of-experts decision model (26B total parameters, about 4B active), post-trained from Gemma 4 26B A4B IT. Official model card: it takes text and optional images and a set of questions, and returns calibrated option probabilities in a single shared-prefix prefill without generating text, with a 131,072-token context window. Ungated open weights are on Hugging Face; it is live on Baseten Model APIs as decision-models/baseten-groundhog-latest. Official price is $0.035 per 1M tokens.

Announced facts

The details so far

Lab
baselabs
Announced
Nov 20, 2026
API
Live · decision-models/baseten-groundhog-latest
Open weights
Published · Ungated open weights on Hugging Face at baselabs/groundhog-1. Official card: it has not yet been scored on the Artificial Analysis Decision Index (Base Labs model card)
Parameters
26B total / ~4B active
Type
Official model card: a 26B mixture-of-experts decision model (about 4B active parameters per token) post-trained from Gemma-4-26B-A4B by Base Labs at Baseten. It answers typed questions (yes/no, choice, and ordered score) from one shared-prefix prefill and returns calibrated probabilities without generating free-form text. Inputs are text and images. Attention uses a block-bidirectional mask on full-attention layers; sliding-window layers stay causal (Base Labs model card and Baseten library)
Context
Official model card and Baseten library: 131,072 tokens (Base Labs model card and Baseten library)
Hosted access
Official model card and Baseten library: live on Baseten Model APIs as decision-models/baseten-groundhog-latest, using the same API as mammoth-1 and elephant-1, at https://inference.baseten.co/v1/systemone (Base Labs model card and Baseten library)
Pricing
Official model card and Baseten library: $0.035 per 1M tokens (Base Labs model card and Baseten library)
License
Baseten's modifications are released under the MIT License; the Gemma 4 26B A4B IT base model is under Apache 2.0. Use of the model is subject to both licenses (Base Labs model card and LICENSE)
Related
Mixture-of-experts sibling of bison-1; separate from mammoth-1, elephant-1, and joey-1

Tags marked unsure are not stated on the lab's own pages.

Next steps

What would let us call it

Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.

  • Publicly announced with a source
  • Usable by the public (API or weights)
  • Listed on an independent board we track
  • Enough results for a rank in a category
  • Holds across two snapshots (crowns only)
Self-reported

What the lab claims

Self-reported. Shown for context; not used in any verdict.

Lab claim: self-reported 77.4 on LongMemEval M and 79.3 on LongMemEval S at 128k tokens in the lab's own run (official groundhog-1 model card).

Receipts

Sources

LABgroundhog-1 (Base Labs model card)huggingface.co/baselabs/groundhog-1LABgroundhog-1 (Baseten Model APIs library)baseten.co/library/groundhog-1/
Editorial

Compare when it lands

Unscored: bison-1. A scored comparison appears once both are on a shared board.

Tracking continues until an independent board lists it.