# JEV-27B-VL vs mammoth-1 > JEV-27B-VL scores 59.5 (C) to mammoth-1's 47.7 (D) for decision models. Prices, MCP, x402, uptime and agent notes side by side. - Canonical: https://www.anchorterminal.com/compare/jev-27b-vl-vs-mammoth-1 - Markdown: https://www.anchorterminal.com/compare/jev-27b-vl-vs-mammoth-1.md (~1,900 tokens) - Slim: https://www.anchorterminal.com/compare/jev-27b-vl-vs-mammoth-1.min.md (~530 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/compare/jev-27b-vl-vs-mammoth-1.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 mammoth-1's 47.7 (D), and leads in 3 of 4 scored categories. mammoth-1 leads on risk. Both do decision models. - 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 - mammoth-1: grade D, 47.7/100, rank #97 of 102 open-weight models. Markdown https://www.anchorterminal.com/tools/mammoth-1.md · JSON https://www.anchorterminal.com/api/v1/tools/mammoth-1.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 ### 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: - Reach, 50 against 40 - Agent interface, 80 against 55 - Documentation and upkeep, 92 against 55 Watch for: Trained on labels distilled from TypeSafe's hosted Jev, whose customer agreement forbids distillation ### mammoth-1 (D) Good for: Agents that want self-hosted routing, triage, classification or judging with probabilities to threshold, many questions per state, on one 80 GB or 96 GB GPU. Ahead on: - Risk, 50 against 45 Watch for: Runs as trained only on OneJev's qev runtime at a pinned commit with the repository's patch ## Score by category | Category | Weight | JEV-27B-VL | mammoth-1 | Edge | | --- | --- | --- | --- | --- | | Capability | 35%, pending | pending | pending | not scored in this run | | Reach | 25% (25 this run) | 50 | 40 | JEV-27B-VL +10 | | Risk | 20% (20 this run) | 45 | 50 | mammoth-1 +5 | | Agent interface | 10% (10 this run) | 80 | 55 | JEV-27B-VL +25 | | Documentation and upkeep | 10% (10 this run) | 92 | 55 | JEV-27B-VL +37 | | Negative events | ≤15 | 0 | 0 | | | **Total** | | **59.5 · C** | **47.7 · D** | | ## Facts side by side | Fact | JEV-27B-VL | mammoth-1 | | --- | --- | --- | | Kind | Open-weight model | Open-weight model | | Vendor | AutoTrust AI Lab | Baseten | | Hosted endpoint | no (local only) | no (local only) | | Transports | | | | Auth | None | None | | Pricing | Free | Free | | x402 | no | no | | Licence | 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 | MIT, named only in the card's metadata (license: other, license_name: mit) with no LICENSE file. Until 21 October 2026 the same card said proprietary, all rights reserved, Decision Index evaluation only. The base, Qwen/Qwen3.5-27B, is Apache-2.0 | | Read-only variant documented | no | no | | llms.txt | no | no | | Last release | 2026-10-02 | 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 | 2.5/5 (4) | 2.3/5 (4) | ## Verdicts **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. **mammoth-1.** A cousin for typed decisions, several questions about one state answered with probabilities from one prefill. It needs about 66 GB in BF16 and a pinned, patched third-party runtime. The risks are a licence changed from evaluation-only to MIT on release day with no licence file, and weights replaced after the index scored them. ## Before you call either ### 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 ### mammoth-1 1. Run `bash setup.sh ` in the pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel image on one CUDA GPU. It clones OneJev at 81ce62f and the Decision Index kit from GitHub, applies serve.patch and pip-installs them, so read it first 2. Load through engine.py's DecisionModel (qev DecisionEngine). Plain Transformers or vLLM run the full-attention layers causally and won't give the trained probabilities 3. Send one state and many questions per request, each choice, yes or no (noul) or score, and read a probability per option 4. Keep requests within the trained length, the report trained at up to 16,384 tokens and engine.py refuses requests over the trained limits 5. The index's scores are for revision b9f2f2cacef2ec178ed25c9ef43e987d3422a639. Pin that revision to get the scored weights, or main for the later ones 6. Text only, the vision encoder is the base's, frozen and untrained for decisions ## Questions ### Which is better for AI agents, JEV-27B-VL or mammoth-1? JEV-27B-VL scores 59.5 (C) on agent readiness against mammoth-1's 47.7 (D), and leads in 3 of 4 scored categories. mammoth-1 leads on risk. ## For agents - This comparison as JSON: https://www.anchorterminal.com/compare/jev-27b-vl-vs-mammoth-1.json, and with the fewest tokens: https://www.anchorterminal.com/compare/jev-27b-vl-vs-mammoth-1.min.md - Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "jev-27b-vl", "b": "mammoth-1"}`. From a terminal: `anchor compare jev-27b-vl mammoth-1` - Each listing in full: https://www.anchorterminal.com/api/v1/tools/jev-27b-vl.json and https://www.anchorterminal.com/api/v1/tools/mammoth-1.json ## Other comparisons with JEV-27B-VL or mammoth-1 - [elephant-1 vs JEV-27B-VL](https://www.anchorterminal.com/compare/elephant-1-vs-jev-27b-vl.md) - [elephant-1 vs mammoth-1](https://www.anchorterminal.com/compare/elephant-1-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