mammoth-1
mammoth-1 is a 27B parameter decision model post-trained from Qwen3.5-27B by Base Labs at Baseten. Provide the model a state (text, optionally with images) and a set of questions and it will return a calibrated probability for every option, answering all questions from one shared-prefix prefill. On tested benchmarks:
- #1 of 208 models on the Jev Decision Index 0.4: 71.24, ahead of Perplexity Decider v1.2 (69.42), Jev 1.14 (+9.0) and Cloudflare Clef (+15.5).
- #1 on a replica of the Artificial Analysis Decision Index: 65.9, ahead of d1-ultra (65).
For quick, cheaper decisions, see the 9B sibling elephant-1.
🗒️ Model Details
| Model | Parameters | Description |
|---|---|---|
| Qwen3.5-27B | 27B | General-purpose base model |
| mammoth-1 | 27B | Post-trained for single-pass, calibrated decisions |
| elephant-1 | 9B | Smaller sibling, fastest decisions |
- Inputs: text and images
- Training: full fine-tune of the language model on text and image decisions; the vision encoder is frozen
- Attention: block-bidirectional mask on full-attention layers.
- Max sequence length: 16,384 tokens
🏃 How to use
Baseten Model APIs
mammoth-1 is free for one week on Baseten Model APIs, with zero data retention on by default. The free week ends 10/27/26 at 11:59 PM PT. The endpoint accepts text and image inputs.
Self-hosted
setup.sh installs the pinned serving runtime (OneJev + serve.patch). It needs one CUDA GPU and the pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel image.
hf download baselabs/mammoth-1 --local-dir mammoth-1 && bash mammoth-1/setup.sh
from qev.engine import DecisionEngine
from qev.schema import SystemOneRequest
engine = DecisionEngine("baselabs/mammoth-1", device="cuda:0")
questions = {
"refund": {"type": "noul", "instructions": "Is the customer asking for a refund?"},
"team": {
"type": "choice",
"instructions": "Which team should handle this?",
"criteria": {"billing": "Charges, refunds, invoices",
"technical": "App or site faults",
"fraud": "Suspected unauthorised use"},
},
"urgency": {
"type": "score",
"instructions": "How urgent is this?",
"criteria": ["Can wait", "Today", "Blocking the customer now"],
},
}
resp, _ = engine.decide(SystemOneRequest(
state="I was charged twice this month, please refund one of them.", questions=questions))
print(resp.answers)
type |
criteria |
answer fields |
|---|---|---|
noul: yes or no |
optional | noul: P(yes) |
choice: one of named options |
{name: description} |
choice, probabilities |
score: ordered levels |
list of levels, lowest first | score, probabilities |
Requests longer than the trained length limits are refused, not truncated.
📊 Performance
Jev Decision Index 0.4
| Model | Decision Index |
|---|---|
| mammoth-1 | 71.24 |
| Perplexity Decider v1.2 | 69.42 |
| elephant-1 | 62.65 |
| Jev 1.14 | 62.2 |
| Cloudflare Clef | 55.7 |
On the public split, mammoth-1 leads in 4 of 5 areas (knowledge & reasoning, language, tools & automation, retrieval & classification, arts & human taste).
Artificial Analysis Decision Index (our replica)
| Model | Score |
|---|---|
| mammoth-1 | 65.9 |
| elephant-1 | 65.2 |
| d1-ultra | 65 |
🔧 Training (all details in the technical report)
- Data: 6.21M decision examples (Mix 8). 58.3% core decision skills, 16.1% safety and abstention, 16.1% judging and expert domains, 9.5% public decision data.
- Objective: cross-entropy plus a Brier calibration term (λ = 1), with a trained "I don't know" option.
- Recipe: 1 epoch (9,859 steps), peak LR 2.7e-6, AdamW (β 0.9/0.95, no weight decay), 3% warm-up, cosine decay, bf16.
- Hardware: 18 nodes × 4 GB300 (72 GPUs).
Citation
@article{baseten2026mammoth,
author = {Base Labs, Baseten},
title = {mammoth-1 and elephant-1: Frontier Decision Models},
journal = {Base Labs},
year = {2026},
note = {https://labs.baseten.co/articles/mammoth-1-and-elephant-1-frontier-decision-models},
}