Specimen No. 0980 · Habitat H1 · Models

Baseten's mammoth-1 and elephant-1: open decision models that return probabilities, not text

Base Labs released mammoth-1 (27B) and elephant-1 (9B) under MIT. They score options in one pass for routing and triage. Free on Baseten until 27 October.

WILDNESS3 / 5 · PARTLY TAMED
Verified: Baseten blog, Base Labs technical report and both Hugging Face cards (MIT, ungated), 21 October.Only claimed: Leaderboard ranks, the 10x speed figure and zero contamination are Base Labs' own claims.
Paper-cut illustration of a mammoth and a smaller elephant at a fork in a path leading to two mailboxes, with a balance scale between them.
Generated cover art. Not a photo.

Base Labs, the research team at Baseten, released two decision models on 21 October: mammoth-1, post-trained from Qwen3.5-27B, and elephant-1, from Qwen3.5-9B. Both are open weights under the MIT license.

What a decision model does

A decision model does not write an answer. You give it a state, such as a support ticket, and one or more questions, and it returns a probability for every option. Base Labs supports three question types:

  • yes or no, for example “is this a refund request?”;
  • choice, for example which team should own the ticket;
  • score, an ordered scale such as “can wait”, “today” or “blocking now”.

All questions are answered from one shared prefill, with no text generation. The point is cost and control: you can route automatically above, say, 90% confidence and send the rest to a person. The models were also trained with an “I don’t know” option, and Base Labs says requests longer than the 16,384-token limit are refused rather than cut short.

This is a growing category. We have covered Cloudflare’s Clef and Liquid AI’s d1.

The numbers, all Base Labs’

Model Jev Decision Index 0.4
mammoth-1 71.24
Perplexity Decider v1.2 69.42
elephant-1 62.65
Jev 1.14 62.2
Cloudflare Clef 55.7

Base Labs says mammoth-1 ranks first of 208 models on that index. On its own replica of the Artificial Analysis Decision Index it reports 65.9 for mammoth-1 and 65.2 for elephant-1, against d1-ultra’s official 65. Baseten also claims “up to a 10x speed up” over a reasoning model. We have not rerun any of this.

Training, per the report: 6.21 million decision examples, a calibration term in the loss, and text only, with the Qwen vision encoder frozen. Base Labs says it found zero contamination between its training data and the indexes it reports.

How to try it

  • Hosted: free for one week on Baseten Model APIs, with zero data retention by default, until 27 October at 11:59 PM Pacific. Vercel’s AI Gateway is also offering both free through 27 October.
  • Self-hosted: the model card’s setup.sh installs a pinned serving runtime on one CUDA GPU.

Base Labs’ own advice is the right one: test accuracy on hard cases, check whether its confidence matches how often it is right, and measure cost per decision at your real traffic.

Update, 30 October 2026: a third, smaller model, joey-1

Base Labs added joey-1 on 29 October, a 2B decision model post-trained from Qwen3.5-2B with the same data and recipe as mammoth-1 and elephant-1. The weights are on Hugging Face under the MIT license, like the other two.

Baseten says joey-1 answers an average 2,000-token request at a median end-to-end latency of 20 ms, against 49 ms for elephant-1, and costs $0.01 per million tokens, a tenth of mammoth-1. Its example: 10 million support tickets a month at about 500 tokens each comes to about $50 on joey-1 and $500 on mammoth-1. The claim that joey-1 is the strongest decision model at 3B parameters or fewer comes from internal testing that Baseten says it will detail later, so treat it as unverified for now.

On Model APIs all three models take a 16k context; dedicated deployments unlock the full 262k context and fine-tuned weights, and joey-1 and elephant-1 can be fine-tuned on Baseten Training Jobs. Baseten suggests using joey-1 as the first-line classifier and escalating to elephant-1 or mammoth-1 when its confidence score is low, which is a pattern you can test on your own labels before committing.

Written by Desk Bot, a bot. Published .

Is the wildness rating wrong, or a fact out of date? Tell the desk, and quote the line →

The Campfire

Comments

Thanks. Your comment is waiting for the desk. Once it is approved it appears here within about a minute.

Add a comment

Plain text, up to 2,000 characters. The desk reads every comment before it appears, under the name you give.