Head to head · Decision models · October 2026 research run
elephant-1 vs joey-1
joey-1 scores 57.1 (C) on agent readiness against elephant-1's 47.6 (D), and leads in every scored category. Both do decision models.
Best decision models for AI agents · All 196 decisions comparisons
Which one, for what
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.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
Serving it needs OneJev at a pinned commit plus the repository's serve.patch, with no released runtime support
joey-1 C
Best for Agents that want self-hosted, low-cost ticket routing or guardrail checks with probabilities to threshold, on a GPU with 8 GB, and can accept a patched runtime.
Ahead on
- Reach, 60 against 55
- Risk, 55 against 50
- Agent interface, 70 against 45
- Documentation and upkeep, 54 against 40
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 | elephant-1 | joey-1 | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 55 | 60 | joey-1 +5 |
| Risk | 20%20 | 50 | 55 | joey-1 +5 |
| Agent interface | 10%10 | 45 | 70 | joey-1 +25 |
| Documentation and upkeep | 10%10 | 40 | 54 | joey-1 +14 |
| Negative events | ≤15 | -2 | -2 | |
| Total | D 47.6/100 | C 57.1/100 |
Facts side by side
| Fact | elephant-1 | joey-1 |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Baseten | Baseten |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | 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 | MIT, named in the card's metadata (license: mit) since the upload of 27 October 2026, with no LICENSE file. The base Qwen/Qwen3.5-2B is Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-21 | 2026-10-29 |
| 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 | 2.3/5 (4) | none |
Verdicts
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.
joey-1
A very small cousin for routing, triage and guardrail checks, answering several typed questions about one state, with text or images, as probabilities from one prefill. It fits an 8 GB GPU in BF16 but runs only through a patched third-party runtime. The risks are weak results on the Decision Index's new-domain tests and no safety results.
Before you call either
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
joey-1
- Start on a CUDA GPU in pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel with
hf download baselabs/joey-1 --local-dir joey-1 && bash joey-1/setup.sh, which clones OneJev at 81ce62f, applies serve.patch and installs the Decision Index kit - Then call
DecisionEngine("baselabs/joey-1", device="cuda:0").decide(SystemOneRequest(state=..., questions=...))from qev, as the card shows - 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
- Expect weaker answers on domains unlike its training mix, and threshold on the returned probability before acting
- Without hardware, Baseten's /v1/systemone serves it as decision-models/baseten-joey-2b-latest with a Baseten key
Questions
Which is better for AI agents, elephant-1 or joey-1?
joey-1 scores 57.1 (C) on agent readiness against elephant-1's 47.6 (D), and leads in every scored category.
Other comparisons with elephant-1 or joey-1
Machine-readable
- This page as Markdown
/compare/elephant-1-vs-joey-1.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/elephant-1.json·/api/v1/tools/joey-1.json - From a terminal
anchor compare elephant-1 joey-1(the CLI) - Over MCP
compare_tools {"a": "elephant-1", "b": "joey-1"}at/mcp, no key