bison-1 vs groundhog-1
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Decision scoring | Decision scoring |
| Published capabilities | Post-trained from Gemma 4 31B IT for classification, routing and rubric scoring. | Post-trained from Gemma 4 26B A4B IT for classification, routing and rubric scoring. |
| Model size | 31B parameters | 26B total / 4B active |
| Access | Public weights and Baseten Model APIs as decision-models/baseten-bison-latest | Public weights and Baseten Model APIs as decision-models/baseten-groundhog-latest |
| Result | Typed decisions and probabilities for supplied options | Typed decisions and probabilities for supplied options |
| Operating limits | Up to 131,072 tokens per question on Baseten Model APIs. | Up to 131,072 tokens per question on Baseten Model APIs. |
| Billing terms | $0.10 USD per million input tokens on Baseten Model APIs. | $0.035 USD per million input tokens on Baseten Model APIs. |
| Sources | Model weights · Additional documentation | Model weights · Additional documentation |
| Inputs | Text, Images | Text, Images |
| Context window | 131,072 tokens | 131,072 tokens |
| Weights | Open weights · MIT and Apache-2.0 | Open weights · MIT and Apache-2.0 |
| Released | Nov 20, 2026 | Nov 20, 2026 |