{ "data": { "a": { "slug": "elephant-1", "name": "elephant-1", "vendor": "Baseten", "vendorUrl": "https://labs.baseten.co", "kind": "weights", "category": "decision-models", "summary": "elephant-1 is Base Labs' open-weight 9B decision model, a full fine-tune of Qwen3.5-9B that returns a probability for every option of typed questions about a state in one prefill. Base Labs is Baseten's research lab.", "url": "https://www.anchorterminal.com/tools/elephant-1", "markdownUrl": "https://www.anchorterminal.com/tools/elephant-1.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/elephant-1.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/elephant-1.json", "repo": "https://huggingface.co/baselabs/elephant-1", "license": "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", "transports": [], "packages": [ { "registry": "huggingface", "name": "baselabs/elephant-1" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository is not gated (checked 2026-10-21). Baseten's hosted Model API for the same model needs a Baseten API key.", "pricing": "free", "pricingNotes": "Free to download under the MIT licence the card's metadata names. Running it costs the hardware, 18.8 GB of BF16 files by the Hub's file list. Baseten also serves it on its Model APIs as decision-models/baseten-elephant-9b-latest, free for a week from 21 October 2026 per Baseten's blog (the announcement gives the end as 27 October 2026, 11:59 PM PT), with no price on the pricing page after that (checked 2026-10-21).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-10-21).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-21" }, "docsUrl": "https://labs.baseten.co/articles/mammoth-1-and-elephant-1-frontier-decision-models", "capabilities": [ "inference.decision", "model.open-weights" ], "tags": [ "open-weights", "model", "decision-model", "full-fine-tune", "calibrated-probabilities", "mit", "safetensors", "self-hosted" ], "lastRelease": "2026-10-21", "graded": true, "anchor": { "graded": true, "score": 47.6, "grade": "D", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1199, "categoryRank": 21, "methodology": "0.6", "run": "2026-10-01", "scores": { "interface": 45, "reach": 55, "risk": 50, "upkeep": 40 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-21" }, "negative": -2, "negativeNotes": [ "21 October 2026. Baseten's blog says elephant-1 is tied for first with d1-ultra on the Artificial Analysis Decision Index, and its library page gives elephant-1 a score of 65.2 there. Artificial Analysis's own page that day lists d1-ultra at 65.25 and Elephant 9B at 64.69, second of the decision models, and states no tie rule. 65.2 is the Base Labs report's own replica figure. The two only match when rounded to whole numbers. Sources: https://www.baseten.co/blog/the-best-decision-models-in-the-world-mammoth-1-and-elephant-1/ , https://www.baseten.co/library/elephant-1/ and https://artificialanalysis.ai/evaluations/artificial-analysis-decision-index (-2)" ], "verdict": "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.", "bestFor": "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.", "strengths": [ "Probabilities for choice, yes or no and score questions, several per request from one shared prefill", "18.8 GB in BF16, so it fits a 24 GB GPU", "Highest model of 8B to 14B on the Jev Decision Index 0.4.1 at 60.26, run on private tests by the index", "Not gated, and Baseten's own Model API serves the same model" ], "weaknesses": [ "Serving it needs OneJev at a pinned commit plus the repository's serve.patch, with no released runtime support", "The licence was proprietary until release day, and MIT now appears only in the metadata with no licence file", "Trained at 16,384 tokens, and longer requests are refused", "The card is two sentences, with no limitations, languages or cut-off", "No quantised build, no safety results and no prompt-injection guidance" ], "agentNotes": [ "Start on a CUDA GPU in pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel with `git clone https://huggingface.co/baselabs/elephant-1 \u0026\u0026 cd elephant-1 \u0026\u0026 bash setup.sh /tmp/w`, which clones OneJev at 81ce62f, applies serve.patch and installs the Decision Index kit", "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", "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" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.3, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "D", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 47.6 } ], "editorialScores": { "interface": 45, "reach": 55, "risk": 50, "upkeep": 40 }, "provenanceScore": 40, "checked": { "categories": { "interface": "2026-10-21", "reach": "2026-10-21", "risk": "2026-10-21", "upkeep": "2026-10-21" }, "last": "2026-10-21", "oldest": "2026-10-21", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "git clone https://huggingface.co/baselabs/elephant-1 \u0026\u0026 cd elephant-1\nbash setup.sh /tmp/w # clones OneJev at 81ce62f, applies serve.patch, installs the Decision Index kit (CUDA image pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel)", "http": "qev serve --model . --port 8000 # OneJev's System One server; its README documents the command, Base Labs doesn't" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/elephant-1" }, "sameCompany": [ "baseten", "mammoth-1" ], "weights": { "trainedBy": "Base Labs (Baseten), on Alibaba's Qwen3.5-9B", "builtOn": "Qwen/Qwen3.5-9B (full fine-tune, Apache-2.0)", "params": "9B", "context": 16384, "goodFor": "Typed decisions with calibrated probabilities over text, several choice, yes or no and score questions about one state in one prefill, for routing, triage, guardrails and judging.", "runtimes": [ "OneJev qev (patched)" ], "builds": [ { "name": "elephant-1", "url": "https://huggingface.co/baselabs/elephant-1", "who": "publisher", "precision": "bf16", "sizeGB": 18.8, "memoryGB": 24, "format": "safetensors", "runsOn": [ "OneJev qev with serve.patch" ], "note": "model.safetensors (18.82 GB), tokenizer, configs and serving bundle, 18.84 GB summed from the Hub's file list. 18.84 × 1.2 = 22.6 GB. No quantised build from Base Labs and no Ollama or LM Studio library entry" } ], "run": "bash setup.sh /tmp/w \u0026\u0026 qev serve --model . --port 8000", "runBuild": "elephant-1", "checked": "2026-10-21", "minMemoryGB": 24 }, "area": "models", "provenance": { "legalEntity": "Baseten Labs, Inc.", "domain": "baseten.co", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "Base Labs is Baseten's research lab (labs.baseten.co, 'A research lab by Baseten'). The legal entity is from the baseten listing's check of Baseten's terms on 30 September 2026.", "The baselabs Hugging Face organisation is unverified, with nine members, among them the report's authors. Baseten's library page, blog and report link to it.", "Nothing is hosted under this listing, so the licence stands in for terms of service and no privacy policy is scored.", "No changelog. www.baseten.co/.well-known/security.txt doesn't exist (an HTML page comes back)." ], "score": 40 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/elephant-1.json" }, "answer": "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.", "b": { "slug": "jev-27b-vl", "name": "JEV-27B-VL", "vendor": "AutoTrust AI Lab", "vendorUrl": "https://huggingface.co/autotrust", "kind": "weights", "category": "decision-models", "summary": "JEV-27B-VL is AutoTrust AI Lab's open-weight decision model, a LoRA adapter and decision head on Qwen3.8-27B that returns option probabilities for questions over text and images, trained on labels distilled from TypeSafe's Jev. It is not a TypeSafe product.", "url": "https://www.anchorterminal.com/tools/jev-27b-vl", "markdownUrl": "https://www.anchorterminal.com/tools/jev-27b-vl.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/jev-27b-vl.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/jev-27b-vl.json", "repo": "https://huggingface.co/autotrust/JEV-27B-VL", "license": "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", "transports": [], "packages": [ { "registry": "huggingface", "name": "autotrust/JEV-27B-VL" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository is not gated (checked 2026-10-21).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0. Running it costs the hardware, 56.0 GB of files in BF16 (the base weights, the 0.45 GB adapter and the tokenizer and configs) by the Hub's file list. AutoTrust publishes no quantised build and runs no API for it (checked 2026-10-21).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-10-21).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-21" }, "docsUrl": "https://huggingface.co/autotrust/JEV-27B-VL", "capabilities": [ "inference.decision", "model.open-weights" ], "tags": [ "open-weights", "model", "decision-model", "lora", "adapter", "multimodal", "vision", "calibrated-probabilities", "apache-2.0", "safetensors", "self-hosted" ], "lastRelease": "2026-10-02", "graded": true, "anchor": { "graded": true, "score": 59.5, "grade": "C", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1199, "categoryRank": 13, "methodology": "0.6", "run": "2026-10-01", "scores": { "interface": 80, "reach": 50, "risk": 45, "upkeep": 92 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-21" }, "negative": 0, "verdict": "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.", "bestFor": "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.", "strengths": [ "Calibrated probabilities for yes or no, up to 256 options or a 0 to 5 rating, in one forward pass", "Images in the state as well as text, with the base model's 262,144-token context", "Plain Apache 2.0 with no gate, and the adapter's training data published", "AutoTrust answered most questions in its discussions within a day or so", "Optional thinking from the unchanged base, off, automatic below a confidence threshold, or always" ], "weaknesses": [ "Trained on labels distilled from TypeSafe's hosted Jev, whose customer agreement forbids distillation", "No quantised build from AutoTrust, so about 67 GB is the floor", "The documented server runs the repository's serve_decide.py and needs a vLLM development build", "One question per request, and image decisions are zero-shot with calibration unmeasured", "No safety results, prompt-injection guidance or security contact" ], "agentNotes": [ "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", "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", "Keep `--max-num-seqs 8`, the card says larger batches return wrong System 1 probabilities on vLLM's multimodal LoRA path", "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", "Choices beyond 16 options use labels the head never saw in training, and the response's adaptation field says wide-labels", "Downscale images to about 448 px to keep vision tokens and latency down", "Treat it as AutoTrust's model, not TypeSafe's, and its request shape differs from TypeSafe's /v1/systemone" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 59.5 } ], "editorialScores": { "interface": 80, "reach": 50, "risk": 45, "upkeep": 92 }, "provenanceScore": 13, "checked": { "categories": { "interface": "2026-10-21", "reach": "2026-10-21", "risk": "2026-10-21", "upkeep": "2026-10-21" }, "last": "2026-10-21", "oldest": "2026-10-21", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "hf download autotrust/JEV-27B-VL --local-dir JEV-27B-VL\nbash JEV-27B-VL/serve.sh # vLLM on :8000 with POST /v1/decide, runs the repository's serve_decide.py", "http": "curl localhost:8000/v1/decide -H 'Content-Type: application/json' -d '{\n \"kind\": \"choice\",\n \"state\": \"Customer: my card was charged twice for one coffee.\",\n \"question\": \"Which team should handle this?\",\n \"options\": [\"billing\", \"shipping\", \"tech support\"]}'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/jev-27b-vl" }, "weights": { "trainedBy": "AutoTrust AI Lab (adapter and decision head) on Alibaba's Qwen3.8-27B", "builtOn": "Qwen/Qwen3.8-27B (LoRA adapter, base weights unchanged, Apache 2.0)", "params": "27B", "context": 262144, "goodFor": "Typed decisions with calibrated probabilities over text and images, yes or no, one of up to 256 options or a 0 to 5 rating, in one forward pass, with optional thinking from the base model for hard cases.", "runtimes": [ "vLLM", "SGLang", "Transformers" ], "builds": [ { "name": "JEV-27B-VL", "url": "https://huggingface.co/autotrust/JEV-27B-VL", "who": "publisher", "precision": "bf16", "sizeGB": 56, "memoryGB": 96, "format": "safetensors", "runsOn": [ "vLLM" ], "note": "Base shards (55.56 GB, vision encoder included), the LoRA adapter (0.45 GB), tokenizer and configs, summed from the Hub's file list. Demo videos and images left out. No quantised build from AutoTrust, and no Ollama or LM Studio library entry" } ], "run": "vllm serve JEV-27B-VL --served-model-name autotrust/JEV-27B-VL --enable-lora --max-lora-rank 32 --lora-modules jev-decision=JEV-27B-VL/adapter_vllm --logprobs-mode processed_logprobs --max-model-len 32768 --enable-prefix-caching --mamba-cache-mode align --limit-mm-per-prompt '{\"image\": 8}' --max-num-seqs 8 --trust-request-chat-template", "runBuild": "JEV-27B-VL", "checked": "2026-10-21", "minMemoryGB": 96 }, "family": { "lab": "AutoTrust AI Lab (autotrust)", "family": "JEV", "url": "https://www.anchorterminal.com/open-weights/#autotrust", "others": [ { "name": "JEV-9B", "url": "https://huggingface.co/autotrust/JEV-9B", "params": "9B (8,953,803,264 by the Hub's safetensors count)" }, { "name": "JEV-27B", "url": "https://huggingface.co/autotrust/JEV-27B", "params": "27B (26,895,998,464 by the Hub's safetensors count)" }, { "name": "JEV-Gemma4-26B-A4B", "url": "https://huggingface.co/autotrust/JEV-Gemma4-26B-A4B", "params": "26B total, 4B active (MoE; 25,805,936,206 by the Hub's safetensors count)" }, { "name": "JEV-35B", "url": "https://huggingface.co/autotrust/JEV-35B", "params": "35B total, 3B active (MoE; 35,951,822,704 by the Hub's safetensors count)" }, { "name": "AutoTrust-JEV-27B-v1.1", "url": "https://huggingface.co/autotrust/AutoTrust-JEV-27B-v1.1", "params": "27B (27,356,728,560 by the Hub's safetensors count)" } ], "olderCount": 1, "unrestrictedCopies": 4 }, "area": "models", "provenance": { "legalEntity": "", "domain": "", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "AutoTrust AI Lab is an unverified Hugging Face organisation with five members. No company site, legal entity or registered domain was found. Its demo at news.guru.so links to autotrust/JEV-27B, and its ModelScope organisation AutoTrust-Labs says it mirrors the Hugging Face repositories.", "Nothing is hosted, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored.", "No changelog. The commit messages on the Hub say what changed, mostly card edits.", "No security.txt, disclosure policy or security contact found." ], "score": 13 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/jev-27b-vl.json" }, "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Baseten", "b": "AutoTrust AI Lab", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "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", "b": "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", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-21", "b": "2026-10-02", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "2.3/5 (4)", "b": "2.5/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "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.", "question": "Which is better for AI agents, elephant-1 or JEV-27B-VL?" } ], "goodFor": [ { "aheadOn": [ "Reach, 55 against 50", "Risk, 50 against 45" ], "also": null, "goodFor": "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.", "slug": "elephant-1", "watchFor": "Serving it needs OneJev at a pinned commit plus the repository's serve.patch, with no released runtime support" }, { "aheadOn": [ "Agent interface, 80 against 45", "Documentation and upkeep, 92 against 40" ], "also": null, "goodFor": "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.", "slug": "jev-27b-vl", "watchFor": "Trained on labels distilled from TypeSafe's hosted Jev, whose customer agreement forbids distillation" } ], "job": { "capability": "inference.decision", "name": "Decision models" }, "others": [ { "json": "https://www.anchorterminal.com/compare/elephant-1-vs-mammoth-1.json", "title": "elephant-1 vs mammoth-1", "url": "https://www.anchorterminal.com/compare/elephant-1-vs-mammoth-1" }, { "json": "https://www.anchorterminal.com/compare/jev-27b-vl-vs-mammoth-1.json", "title": "JEV-27B-VL vs mammoth-1", "url": "https://www.anchorterminal.com/compare/jev-27b-vl-vs-mammoth-1" } ], "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 5, "edge": "elephant-1", "elephant-1": 55, "jev-27b-vl": 50, "key": "reach", "name": "Reach", "weight": 25 }, { "by": 5, "edge": "elephant-1", "elephant-1": 50, "jev-27b-vl": 45, "key": "risk", "name": "Risk", "weight": 20 }, { "by": 35, "edge": "jev-27b-vl", "elephant-1": 45, "jev-27b-vl": 80, "key": "interface", "name": "Agent interface", "weight": 10 }, { "by": 52, "edge": "jev-27b-vl", "elephant-1": 40, "jev-27b-vl": 92, "key": "upkeep", "name": "Documentation and upkeep", "weight": 10 } ], "summary": "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.", "tutorials": [], "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/elephant-1-vs-jev-27b-vl", "json": "https://www.anchorterminal.com/compare/elephant-1-vs-jev-27b-vl.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/elephant-1-vs-jev-27b-vl.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/elephant-1-vs-jev-27b-vl.min.md" }, "markdown": "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.\n\n- 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\n- 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\n- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md\n- All 193 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md\n\n## Which one, for what\n\n### elephant-1 (D)\n\nGood 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.\n\nAhead on:\n- Reach, 55 against 50\n- Risk, 50 against 45\n\nWatch for: Serving it needs OneJev at a pinned commit plus the repository's serve.patch, with no released runtime support\n\n### JEV-27B-VL (C)\n\nGood 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.\n\nAhead on:\n- Agent interface, 80 against 45\n- Documentation and upkeep, 92 against 40\n\nWatch for: Trained on labels distilled from TypeSafe's hosted Jev, whose customer agreement forbids distillation\n\n\n## Score by category\n\n| Category | Weight | elephant-1 | JEV-27B-VL | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 55 | 50 | elephant-1 +5 |\n| Risk | 20% (20 this run) | 50 | 45 | elephant-1 +5 |\n| Agent interface | 10% (10 this run) | 45 | 80 | JEV-27B-VL +35 |\n| Documentation and upkeep | 10% (10 this run) | 40 | 92 | JEV-27B-VL +52 |\n| Negative events | ≤15 | -2 | 0 | |\n| **Total** | | **47.6 · D** | **59.5 · C** | |\n\n## Facts side by side\n\n| Fact | elephant-1 | JEV-27B-VL |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Baseten | AutoTrust AI Lab |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| 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 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-21 | 2026-10-02 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Agent reviews | 2.3/5 (4) | 2.5/5 (4) |\n\n## Verdicts\n\n**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.\n\n**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.\n\n## Before you call either\n\n### elephant-1\n\n1. Start on a CUDA GPU in pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel with `git clone https://huggingface.co/baselabs/elephant-1 \u0026\u0026 cd elephant-1 \u0026\u0026 bash setup.sh /tmp/w`, which clones OneJev at 81ce62f, applies serve.patch and installs the Decision Index kit\n2. 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\n3. 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\n4. Keep each request under 16,384 tokens, the trained length, or the engine refuses it\n5. Group the questions about one state in one request, since the state is read once and shared\n6. 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\n\n### JEV-27B-VL\n\n1. 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\n2. 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\n3. Keep `--max-num-seqs 8`, the card says larger batches return wrong System 1 probabilities on vLLM's multimodal LoRA path\n4. 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\n5. Choices beyond 16 options use labels the head never saw in training, and the response's adaptation field says wide-labels\n6. Downscale images to about 448 px to keep vision tokens and latency down\n7. Treat it as AutoTrust's model, not TypeSafe's, and its request shape differs from TypeSafe's /v1/systemone\n\n## Questions\n\n### Which is better for AI agents, elephant-1 or JEV-27B-VL?\n\nJEV-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.\n\n\n## For agents\n\n- 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\n- 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`\n- 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\n\n## Other comparisons with elephant-1 or JEV-27B-VL\n\n- [elephant-1 vs mammoth-1](https://www.anchorterminal.com/compare/elephant-1-vs-mammoth-1.md)\n- [JEV-27B-VL vs mammoth-1](https://www.anchorterminal.com/compare/jev-27b-vl-vs-mammoth-1.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-22", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.6", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "elephant-1 vs JEV-27B-VL", "url": "" } ], "description": "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.", "facts": [ "elephant-1 D 47.6", "JEV-27B-VL C 59.5", "scores" ], "h1": "elephant-1 vs JEV-27B-VL", "image": "https://www.anchorterminal.com/assets/og/compare-elephant-1-vs-jev-27b-vl.png", "path": "/compare/elephant-1-vs-jev-27b-vl", "published": "2026-10-01", "section": "tools", "title": "elephant-1 vs JEV-27B-VL for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-22", "url": "https://www.anchorterminal.com/compare/elephant-1-vs-jev-27b-vl" }, "tokens": { "markdown": 1950, "slim": 530 }, "version": 1 }