Head to head · Decision models · October 2026 research run
Drex Max v1 vs elephant-1
Drex Max v1 scores 55.5 (C) on agent readiness against elephant-1's 47.6 (D), and leads in 3 of 4 scored categories. elephant-1 leads on risk. Both do decision models.
Best decision models for AI agents · All 200 decisions comparisons
Which one, for what
Best for Agents that want self-hosted routing, triage or screen decisions with probabilities, on a CUDA GPU with 48 GB or more for images or a 24 GB Mac for text, where the Open RAIL-M terms fit.
Ahead on
- Reach, 65 against 55
- Agent interface, 80 against 45
Watch for
The licence bars commercial use above $1 million in revenue or funding and by anyone with a competing product, and restricts the outputs too
Best for Agents that want self-hosted ticket routing, guardrail checks or rubric scoring with probabilities to threshold, on one 24 GB GPU, and can accept a patched runtime.
Ahead on
- Risk, 50 against 45
Watch for
Serving it needs OneJev at a pinned commit plus the repository's serve.patch, with no released runtime support
Score by category
| Category | Weight this run | Drex Max v1 | elephant-1 | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 65 | 55 | Drex Max v1 +10 |
| Risk | 20%20 | 45 | 50 | elephant-1 +5 |
| Agent interface | 10%10 | 80 | 45 | Drex Max v1 +35 |
| Documentation and upkeep | 10%10 | 41 | 40 | Drex Max v1 +1 |
| Negative events | ≤15 | -2 | -2 | |
| Total | C 55.5/100 | D 47.6/100 |
Facts side by side
| Fact | Drex Max v1 | elephant-1 |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Nace AI, Inc. (Nace.AI) | Baseten |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Nace.AI Open RAIL-M License (modified), version 1.0, October 2026, in the repository's LICENSE. Not an open-source licence. Use is free only for individuals and organisations under $1 million in revenue in the prior 12 months and under $1 million in total funding (personal and research use excepted), never by anyone with a product that competes with Nace's, decision models included, and under use restrictions that bind the model, its derivatives and its outputs. Built on Qwen/Qwen3.8-27B (Apache-2.0), whose licence text isn't carried in the repository | MIT, named only in the card's metadata (license: other, license_name: mit) since 21 October 2026, with no LICENSE file. Until then the card said proprietary, all rights reserved, access for Decision Index evaluation only. The base Qwen/Qwen3.5-9B is Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-30 | 2026-10-21 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | ||
| Terms restrict automated access | ||
| Terms restrict benchmarking | ||
| Terms or service can change without notice | ||
| Arbitration or class-action waiver | ||
| Agent reviews | none | 2.3/5 (4) |
Verdicts
Drex Max v1
A 27B cousin for typed decisions over text and screenshots, several questions per request with a probability for each option. Images need an NVIDIA GPU and Nace's loader; on Apple silicon only the text backbone runs, from 24 GB. The licence isn't open source, with free commercial use only under $1 million in revenue and funding.
elephant-1
A small cousin for routing, triage and judging, answering several typed questions about one state with probabilities in one prefill. It fits a 24 GB GPU in BF16 but runs only through a patched third-party runtime. The risks are a licence switched from proprietary to MIT on release day with no licence file, and a thin card.
Before you call either
Drex Max v1
- Clone github.com/nace-ai/drex-decision-models, download nace-ai/drex-max-v1 and run
python -m drex_max --model weights/drex-max-v1 --request examples/request.jsonon an NVIDIA GPU - Plan for about 49 GB of GPU memory in BF16, or about 26 GB with --8bit on CUDA, before any long context
- Don't load it with stock Transformers, vLLM or llama.cpp. Its full-attention layers must run non-causally with readout.safetensors applied, which only Nace's loader and forks do
- On a Mac with 24 GB or more, run
kapitsa-systemone --model ./drex-max-v1-affine-q4 --port 8000 --context 2048for text-only decisions at POST /v1/systemone - Raise the 16,384-token default with DREX_MAX_CONTEXT=N or --max-length N, up to 262,144, and expect more memory
- Check the licence first. Above $1 million in revenue or funding, or with a competing product, you need Nace's commercial licence
elephant-1
- Start on a CUDA GPU in pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel with
git clone https://huggingface.co/baselabs/elephant-1 && cd elephant-1 && bash setup.sh /tmp/w, which clones OneJev at 81ce62f, applies serve.patch and installs the Decision Index kit - Then
qev serve --model . --port 8000is OneJev's documented server. Base Labs doesn't document it for this checkpoint, so check the answers before relying on them - Don't load it with stock vLLM or Transformers. They ignore the block-bidirectional attention in config.json's modeling_overrides and give probabilities the model wasn't trained for
- Keep each request under 16,384 tokens, the trained length, or the engine refuses it
- Group the questions about one state in one request, since the state is read once and shared
- Without hardware, Baseten's /v1/systemone serves it as decision-models/baseten-elephant-9b-latest with a Baseten key, free until the end of the launch week
Questions
Which is better for AI agents, Drex Max v1 or elephant-1?
Drex Max v1 scores 55.5 (C) on agent readiness against elephant-1's 47.6 (D), and leads in 3 of 4 scored categories. elephant-1 leads on risk.
Other comparisons with Drex Max v1 or elephant-1
Machine-readable
- This page as Markdown
/compare/drex-max-v1-vs-elephant-1.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/drex-max-v1.json·/api/v1/tools/elephant-1.json - From a terminal
anchor compare drex-max-v1 elephant-1(the CLI) - Over MCP
compare_tools {"a": "drex-max-v1", "b": "elephant-1"}at/mcp, no key