Try on Baseten • Technical report • Blog

elephant-1

elephant-1 is a 9B parameter decision model post-trained from Qwen3.5-9B by Base Labs at Baseten. Provide the model a state 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:

Best model under 15B on the Jev Decision Index 0.4: 62.65, tied #8 of 208 models.
65.2 on a replica of the Artificial Analysis Decision Index: level with d1-ultra (65).

For tasks that need broader general knowledge, see the 27B sibling mammoth-1.

🗒️ Model Details

Model	Parameters	Description
Qwen3.5-9B	9B	General-purpose base model
elephant-1	9B	Post-trained for single-pass, calibrated decisions
mammoth-1	27B	Larger sibling, highest accuracy

Training: full fine-tune, text only (we freeze the vision encoder)
Attention: block-bidirectional mask on full-attention layers.
Max sequence length: 16,384 tokens

🏃 How to use

Baseten Model APIs

elephant-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.

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/elephant-1 --local-dir elephant-1 && bash elephant-1/setup.sh

from qev.engine import DecisionEngine
from qev.schema import SystemOneRequest

engine = DecisionEngine("baselabs/elephant-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, elephant-1 narrowly trails mammoth-1 in every area and beats Jev 1.14 in all five (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 (5,546 steps), peak LR 3.5e-6, AdamW (β 0.9/0.95, no weight decay), 3% warm-up, cosine decay, bf16.
Hardware: 16 nodes × 8 H100 (128 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},
}