# elephant-1 vs JEV-27B-VL

> JEV-27B-VL scores 59.5 (C) to elephant-1's 47.6 (D) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/elephant-1-vs-jev-27b-vl
- Markdown: https://www.anchorterminal.com/compare/elephant-1-vs-jev-27b-vl.md (~1,950 tokens)
- Slim: https://www.anchorterminal.com/compare/elephant-1-vs-jev-27b-vl.min.md (~530 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/elephant-1-vs-jev-27b-vl.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-10-22

JEV-27B-VL scores 59.5 (C) on agent readiness against elephant-1's 47.6 (D), and leads in 2 of 4 scored categories. elephant-1 leads on reach and risk. Both do decision models.

- elephant-1: grade D, 47.6/100, rank #98 of 102 open-weight models. Markdown https://www.anchorterminal.com/tools/elephant-1.md · JSON https://www.anchorterminal.com/api/v1/tools/elephant-1.json
- JEV-27B-VL: grade C, 59.5/100, rank #60 of 102 open-weight models. Markdown https://www.anchorterminal.com/tools/jev-27b-vl.md · JSON https://www.anchorterminal.com/api/v1/tools/jev-27b-vl.json
- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md
- All 193 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md

## Which one, for what

### elephant-1 (D)

Good 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:
- Reach, 55 against 50
- 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

### JEV-27B-VL (C)

Good for: Agents that want self-hosted routing, triage, ranking or judging over text and screenshots with probabilities to threshold, on one 80 GB GPU or a 96 GB machine.

Ahead on:
- Agent interface, 80 against 45
- Documentation and upkeep, 92 against 40

Watch for: Trained on labels distilled from TypeSafe's hosted Jev, whose customer agreement forbids distillation


## Score by category

| Category | Weight | elephant-1 | JEV-27B-VL | Edge |
| --- | --- | --- | --- | --- |
| Capability | 35%, pending | pending | pending | not scored in this run |
| Reach | 25% (25 this run) | 55 | 50 | elephant-1 +5 |
| Risk | 20% (20 this run) | 50 | 45 | elephant-1 +5 |
| Agent interface | 10% (10 this run) | 45 | 80 | JEV-27B-VL +35 |
| Documentation and upkeep | 10% (10 this run) | 40 | 92 | JEV-27B-VL +52 |
| Negative events | ≤15 | -2 | 0 | |
| **Total** | | **47.6 · D** | **59.5 · C** | |

## Facts side by side

| Fact | elephant-1 | JEV-27B-VL |
| --- | --- | --- |
| Kind | Open-weight model | Open-weight model |
| Vendor | Baseten | AutoTrust AI Lab |
| 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 | Apache-2.0 for AutoTrust's System 1 adapter and decision head. The base Qwen3.8-27B weights in the repository are Alibaba's, unchanged, also Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-21 | 2026-10-02 |
| 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) | 2.5/5 (4) |

## 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.

**JEV-27B-VL.** A cousin for typed decisions with probabilities over text and images, answering in one pass with optional thinking. It needs about 67 GB in BF16 on vLLM, with no AutoTrust 4-bit build or hosted API. The main risks are labels distilled from TypeSafe's Jev against its customer terms and serving through a repository script on a vLLM development build.

## Before you call either

### elephant-1

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
2. Then `qev serve --model . --port 8000` is OneJev's documented server. Base Labs doesn't document it for this checkpoint, so check the answers before relying on them
3. 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
4. Keep each request under 16,384 tokens, the trained length, or the engine refuses it
5. Group the questions about one state in one request, since the state is read once and shared
6. 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

### JEV-27B-VL

1. Quickest start is `hf download autotrust/JEV-27B-VL` then `bash JEV-27B-VL/serve.sh`, which serves POST /v1/decide on port 8000, but it runs the repository's serve_decide.py on a September 2026 vLLM development build
2. On a released vLLM use plain `vllm serve` with `--enable-lora --lora-modules jev-decision=JEV-27B-VL/adapter_vllm` and do the card's client-side arithmetic with decision_head.json and calibration.json
3. Keep `--max-num-seqs 8`, the card says larger batches return wrong System 1 probabilities on vLLM's multimodal LoRA path
4. When calling /v1/completions or /v1/chat/completions yourself pass top_k 0 and top_p 1.0, or generation_config.json's top_k 20 and top_p 0.95 truncate the probabilities
5. Choices beyond 16 options use labels the head never saw in training, and the response's adaptation field says wide-labels
6. Downscale images to about 448 px to keep vision tokens and latency down
7. Treat it as AutoTrust's model, not TypeSafe's, and its request shape differs from TypeSafe's /v1/systemone

## Questions

### Which is better for AI agents, elephant-1 or JEV-27B-VL?

JEV-27B-VL scores 59.5 (C) on agent readiness against elephant-1's 47.6 (D), and leads in 2 of 4 scored categories. elephant-1 leads on reach and risk.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/elephant-1-vs-jev-27b-vl.json, and with the fewest tokens: https://www.anchorterminal.com/compare/elephant-1-vs-jev-27b-vl.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "elephant-1", "b": "jev-27b-vl"}`. From a terminal: `anchor compare elephant-1 jev-27b-vl`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/elephant-1.json and https://www.anchorterminal.com/api/v1/tools/jev-27b-vl.json

## Other comparisons with elephant-1 or JEV-27B-VL

- [elephant-1 vs mammoth-1](https://www.anchorterminal.com/compare/elephant-1-vs-mammoth-1.md)
- [JEV-27B-VL vs mammoth-1](https://www.anchorterminal.com/compare/jev-27b-vl-vs-mammoth-1.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp