Baseten · Decision
Mammoth 1
Mammoth-1 is a 27B decision model from Baseten's Base Labs, fine-tuned from Qwen3.5-27B for classification, routing, and scoring. It answers multiple-choice, yes/no, and ordered scoring questions with probabilities over predefined options rather than generated text. Shared-prefix caching reuses context across questions, while per-option probabilities support confidence thresholds and escalation decisions.
Evidence and sources
All rankings:
#172 on OpenRouter today
#225 on OpenRouter this week
#251 on OpenRouter this monthSources: NeuralWatt data, OpenRouter Decision Models data docs, Vercel AI Gateway data, llminfo researchPrimary data from NeuralWatt
from OpenRouter Decision Models: name
from Vercel AI Gateway: description
from llminfo research: release date
Advantages and trade-offs
Compared with 10 representative decision models
Trade-offs
Input & output
Inputs as stated by providers; output from the model’s typeText
Images
Choices and scores
Also known as: baseten/mammoth-1
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works