{ "data": { "similar": [ { "grade": "C", "json": "https://www.anchorterminal.com/tools/jev-27b-vl.json", "name": "JEV-27B-VL", "score": 59.5, "shared": [ "inference.decision", "model.open-weights" ], "slug": "jev-27b-vl" }, { "grade": "D", "json": "https://www.anchorterminal.com/tools/mammoth-1.json", "name": "mammoth-1", "score": 47.7, "shared": [ "inference.decision", "model.open-weights" ], "slug": "mammoth-1" }, { "grade": "D", "json": "https://www.anchorterminal.com/tools/elephant-1.json", "name": "elephant-1", "score": 47.6, "shared": [ "inference.decision", "model.open-weights" ], "slug": "elephant-1" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/qwen3-embedding-8b.json", "name": "Qwen3-Embedding-8B", "score": 74.7, "shared": [ "model.open-weights" ], "slug": "qwen3-embedding-8b" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/gemma-4-31b-it.json", "name": "Gemma 4 31B IT", "score": 74.1, "shared": [ "model.open-weights" ], "slug": "gemma-4-31b-it" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/openai-decisions-api.json", "name": "OpenAI Decisions API", "score": 73.1, "shared": [ "inference.decision" ], "slug": "openai-decisions-api" } ], "tool": { "slug": "joey-1", "name": "joey-1", "vendor": "Baseten", "vendorUrl": "https://labs.baseten.co", "kind": "weights", "category": "decision-models", "summary": "joey-1 is Base Labs' open-weight 2B decision model, a full fine-tune of Qwen3.5-2B that takes text and images and 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/joey-1", "markdownUrl": "https://www.anchorterminal.com/tools/joey-1.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/joey-1.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/joey-1.json", "repo": "https://huggingface.co/baselabs/joey-1", "license": "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", "transports": [], "packages": [ { "registry": "huggingface", "name": "baselabs/joey-1" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository is not gated (checked 2026-10-30). 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, 5.47 GB of BF16 files by the Hub's file list. Baseten also serves it on its Model APIs as decision-models/baseten-joey-2b-latest at $0.01 per million input tokens, with cached input and output at $0.00, per its library page (checked 2026-10-30).", "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 2026-10-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-30" }, "docsUrl": "https://huggingface.co/baselabs/joey-1", "capabilities": [ "inference.decision", "model.open-weights" ], "tags": [ "open-weights", "model", "decision-model", "full-fine-tune", "calibrated-probabilities", "vision", "mit", "safetensors", "self-hosted" ], "lastRelease": "2026-10-29", "graded": true, "anchor": { "graded": true, "score": 57.1, "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": 1239, "categoryRank": 16, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 70, "reach": 60, "risk": 55, "upkeep": 54 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "capability", "name": "Capability", "weight": 35, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending for this listing. Nobody independent has published results for it in at least two areas yet, so its weight is shared across the other four and the total is capped at 61 until they do or our own runs start." }, { "key": "reach", "name": "Reach", "weight": 25, "effectiveWeight": 38.46, "score": 60, "points": 23.08, "reason": "Memory 30 of 30, the BF16 repository is 5.47 GB, 6.6 GB with a fifth added, so it fits 8 GB. Runtimes 0, only a third party's OneJev runtime patched by the repository's serve.patch applies the model's changed attention and readout. Builds 0, no quantised build. Terms 15, MIT in the card's metadata with nothing added, though there's no licence file. Download 10, not gated. Hosted 5, Baseten's own Model API serves it.", "checked": "2026-10-30" }, { "key": "risk", "name": "Risk", "weight": 20, "effectiveWeight": 30.77, "score": 55, "points": 16.92, "reason": "File safety 15 of 25, safetensors only, but serving it means running the repository's setup.sh and patch. Provenance 15, the organisation Baseten links to, with a checksum on every file. Safety evaluation 0, none for the model; a guardrail benchmark in an open pull request measures task accuracy. Agent guidance 5, abstention and threshold advice only. Licence risk 15, MIT unchanged since upload. Security programme 5, Baseten's disclosure address but no public advisories.", "checked": "2026-10-30" }, { "key": "interface", "name": "Agent interface", "weight": 10, "effectiveWeight": 15.38, "score": 70, "points": 10.77, "reason": "Read as a decision model, by what it takes and returns. Chat template 10 of 20, the base's template is there but the decision prompt is built in code. Tool-calling format 25, the card documents the request, the answer fields and the call in OneJev's qev. Trained tool calling 20, several questions per request from one prefill. Structured output 15, how to ask for each typed answer and what comes back. Reasoning control 0, it doesn't think. Context 0, trained at 16,384 tokens and refused beyond.", "checked": "2026-10-30" }, { "key": "upkeep", "name": "Documentation and upkeep", "weight": 10, "effectiveWeight": 15.38, "score": 54, "points": 8.31, "reason": "Model card 14 of 20, five of the seven items, no limitations or cut-off. Training data 5, the mix described with no data published and no cut-off. Last change 20, the card changed on 29 October. Responsiveness 0, nobody has asked anything yet. Version policy 5, a first release. File health 10, the files and card agree.", "checked": "2026-10-30" } ], "assessment": { "date": "2026-10-30", "basis": "public evidence", "confidence": "low", "notes": { "capability": "Pending for this listing. Independent results were found in 0 areas (none), and Capability needs 2. Its weight is shared across the other four categories and the total is capped at 61 until there are more, or our own runs start.", "interface": "Read as a decision model, by what it takes and returns. Chat template 10 of 20, the base's template is there but the decision prompt is built in code. Tool-calling format 25, the card documents the request, the answer fields and the call in OneJev's qev. Trained tool calling 20, several questions per request from one prefill. Structured output 15, how to ask for each typed answer and what comes back. Reasoning control 0, it doesn't think. Context 0, trained at 16,384 tokens and refused beyond.", "reach": "Memory 30 of 30, the BF16 repository is 5.47 GB, 6.6 GB with a fifth added, so it fits 8 GB. Runtimes 0, only a third party's OneJev runtime patched by the repository's serve.patch applies the model's changed attention and readout. Builds 0, no quantised build. Terms 15, MIT in the card's metadata with nothing added, though there's no licence file. Download 10, not gated. Hosted 5, Baseten's own Model API serves it.", "risk": "File safety 15 of 25, safetensors only, but serving it means running the repository's setup.sh and patch. Provenance 15, the organisation Baseten links to, with a checksum on every file. Safety evaluation 0, none for the model; a guardrail benchmark in an open pull request measures task accuracy. Agent guidance 5, abstention and threshold advice only. Licence risk 15, MIT unchanged since upload. Security programme 5, Baseten's disclosure address but no public advisories.", "upkeep": "Model card 14 of 20, five of the seven items, no limitations or cut-off. Training data 5, the mix described with no data published and no cut-off. Last change 20, the card changed on 29 October. Responsiveness 0, nobody has asked anything yet. Version policy 5, a first release. File health 10, the files and card agree." }, "sources": [ { "what": "model card, read 30 October 2026", "url": "https://huggingface.co/baselabs/joey-1", "seen": "2026-10-30" }, { "what": "the card as uploaded on 27 October 2026, MIT from the start", "url": "https://huggingface.co/baselabs/joey-1/raw/3903da0d1252277671a0865daeec29c1965f1cb5/README.md", "seen": "2026-10-30" }, { "what": "Hub API, card data, gating, downloads, providers, parameter count", "url": "https://huggingface.co/api/models/baselabs/joey-1", "seen": "2026-10-30" }, { "what": "eval results from the open pull request #1, safeagents judge bench", "url": "https://huggingface.co/api/models/baselabs/joey-1?expand[]=evalResults", "seen": "2026-10-30" }, { "what": "file tree with sizes and SHA-256 for LFS files", "url": "https://huggingface.co/api/models/baselabs/joey-1/tree/main?recursive=true", "seen": "2026-10-30" }, { "what": "commit history", "url": "https://huggingface.co/api/models/baselabs/joey-1/commits/main", "seen": "2026-10-30" }, { "what": "config, modeling_overrides, positions", "url": "https://huggingface.co/baselabs/joey-1/raw/main/config.json", "seen": "2026-10-30" }, { "what": "Decision Index engine, request and answer fields, length refusal", "url": "https://huggingface.co/baselabs/joey-1/raw/main/engine.py", "seen": "2026-10-30" }, { "what": "serving setup, OneJev and kit at pinned commits", "url": "https://huggingface.co/baselabs/joey-1/raw/main/setup.sh", "seen": "2026-10-30" }, { "what": "patch to OneJev's engine, prompt and readout, same blob as elephant-1's", "url": "https://huggingface.co/baselabs/joey-1/raw/main/serve.patch", "seen": "2026-10-30" }, { "what": "base file tree, licence and chat template hash compared", "url": "https://huggingface.co/api/models/Qwen/Qwen3.5-2B/tree/main?recursive=true", "seen": "2026-10-30" }, { "what": "organisation members", "url": "https://huggingface.co/api/organizations/baselabs/members", "seen": "2026-10-30" }, { "what": "baselabs datasets, joey-1-decision-index gated manually", "url": "https://huggingface.co/api/datasets?author=baselabs", "seen": "2026-10-30" }, { "what": "discussions, authors and dates counted by script, no text read", "url": "https://huggingface.co/baselabs/joey-1/discussions", "seen": "2026-10-30" }, { "what": "Baseten library page, developer Base Labs, MIT, link to the repository, price, model slug, the top-2B claim", "url": "https://www.baseten.co/library/joey-1/", "seen": "2026-10-30" }, { "what": "launch blog of 29 October 2026, speed and price claims, availability", "url": "https://www.baseten.co/blog/decisions-for-a-penny-introducing-joey-1/", "seen": "2026-10-30" }, { "what": "Jev Decision Index 0.4.1 data, generated 29 October 2026, joey-1's scores, ranks, latency and notes", "url": "https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/main/data/index.json", "seen": "2026-10-30" }, { "what": "Decision Index README, ranked by the Full score, unofficial, not affiliated with TypeSafe AI", "url": "https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/main/README.md", "seen": "2026-10-30" }, { "what": "Artificial Analysis Decision Index page, no joey-1 entry found", "url": "https://artificialanalysis.ai/evaluations/artificial-analysis-decision-index", "seen": "2026-10-30" }, { "what": "the guardrail benchmark in pull request #1, created 30 October 2026", "url": "https://huggingface.co/datasets/harness-hub/safeagents-judge-bench", "seen": "2026-10-30" } ], "openQuestions": [ "Whether OneJev's qev after setup.sh serves this checkpoint as trained couldn't be checked without running it. The Decision Index's agreement check (99.60 per cent on 831 rows) suggests it does", "The deduction rests on the index ranking by its Full score. If the founder reads the library page's 'top 2B model' as meaning the public split the card names, it lapses", "The 'fastest decision model available' wording in the launch post wasn't found on a Baseten page. The blog says 'our fastest' and '5x faster than comparable decision models' at a 20 ms P50 on Baseten's production serving, which nobody else has measured. The index's own timing on one RTX PRO 6000 puts joey-1 153rd of 247 by median latency", "Baseten's decision-models doc, its trust centre and security.txt weren't re-read today (the robots.txt reads for www.baseten.co, docs.baseten.co and artificialanalysis.ai were refused in this session), so agent guidance and the security programme rest on the 21 October and 30 September checks", "The Hub counts 2.72B parameters, about 0.45B more than the Qwen3.5-2B base's 2.27B, and the card doesn't say why", "The card's 'joey-1 #37 of 230' on the public split doesn't match the index's public rank today (47th of 247)" ] }, "negative": -2, "negativeNotes": [ "29 October 2026. Baseten's library page says 'On release (October 2026), joey-1 is the top 2B model on the Jev Decision Index 0.4.' The index (edition 0.4.1, joey-1 added 29 October in PR #330) ranks by its Full score and says the public benchmarks don't count. On it joey-1 has 35.91, 149th of 247, below StartLux-Decision v1.1 2B at 40.11 on the same Qwen3.5-2B base. Only the public score (63.30, first of the models under 4B) supports the claim, and the card names that split while the library page doesn't. Sources: https://www.baseten.co/library/joey-1/ and https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/main/data/index.json (-2)" ], "verdict": "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.", "bestFor": "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.", "strengths": [ "Probabilities for choice, yes or no and score questions, several per request from one shared prefill, over text and images", "5.5 GB in BF16, so it fits an 8 GB GPU", "Highest public score of every model under 4B on the Jev Decision Index 0.4.1 at 63.30", "The card documents the request, answer fields and a runnable call, and the licence has been MIT since upload", "Not gated, and Baseten's own Model API serves the same model at $0.01 per million input tokens" ], "weaknesses": [ "Serving it needs OneJev at a pinned commit plus the repository's serve.patch, with no released runtime support", "Full score 35.91 on the Decision Index's private tests, 10.2 on new domains, with one test excluded for signs of training overlap", "Trained at 16,384 tokens, and longer requests are refused", "No quantised build, no safety results and no prompt-injection guidance", "No LICENSE file, and the Apache-2.0 base's licence isn't carried" ], "agentNotes": [ "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 \u0026\u0026 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" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 57.1 } ], "editorialScores": { "interface": 70, "reach": 60, "risk": 55, "upkeep": 54 }, "provenanceScore": 50, "checked": { "categories": { "interface": "2026-10-30", "reach": "2026-10-30", "risk": "2026-10-30", "upkeep": "2026-10-30" }, "last": "2026-10-30", "oldest": "2026-10-30", "stale": false, "staleAfterDays": 90 }, "scoreHistory": [ { "date": "2026-10-30", "grade": "C", "kind": "listed", "method": "0.7", "score": 57.1 } ] }, "connect": { "install": "hf download baselabs/joey-1 --local-dir joey-1 \u0026\u0026 bash joey-1/setup.sh # clones OneJev at 81ce62f, applies serve.patch, installs the Decision Index kit (CUDA image pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel)\n# then, in Python:\nfrom qev.engine import DecisionEngine\nfrom qev.schema import SystemOneRequest\nengine = DecisionEngine(\"baselabs/joey-1\", device=\"cuda:0\")\nresp, _ = engine.decide(SystemOneRequest(state=..., questions={...}))" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/joey-1" }, "sameCompany": [ "baseten", "elephant-1", "mammoth-1" ], "weights": { "trainedBy": "Base Labs (Baseten), on Alibaba's Qwen3.5-2B", "builtOn": "Qwen/Qwen3.5-2B (full fine-tune, Apache-2.0)", "params": "2B", "context": 16384, "goodFor": "Cheap typed decisions with calibrated probabilities over text and images, several choice, yes or no and score questions about one state in one prefill, for routing, triage and guardrails on a small GPU.", "runtimes": [ "OneJev qev (patched)" ], "builds": [ { "name": "joey-1", "url": "https://huggingface.co/baselabs/joey-1", "who": "publisher", "precision": "bf16", "sizeGB": 5.5, "memoryGB": 8, "format": "safetensors", "runsOn": [ "OneJev qev with serve.patch" ], "note": "model.safetensors (5.44 GB), tokenizer, configs, banner and serving bundle, 5.47 GB summed from the Hub's file list. 5.47 × 1.2 = 6.6 GB. No quantised build from Base Labs and no Ollama or LM Studio library entry" } ], "run": "bash setup.sh \u0026\u0026 python -c 'from qev.engine import DecisionEngine; DecisionEngine(\"baselabs/joey-1\", device=\"cuda:0\")'", "runBuild": "joey-1", "checked": "2026-10-30", "minMemoryGB": 8 }, "family": { "lab": "Base Labs (Baseten)", "family": "Base Labs decision models (-1)", "url": "https://www.anchorterminal.com/open-weights/#baselabs", "others": [ { "name": "elephant-1", "url": "https://huggingface.co/baselabs/elephant-1", "params": "9B (9,409,813,744 by the Hub's safetensors count)", "listing": "https://www.anchorterminal.com/tools/elephant-1" }, { "name": "mammoth-1", "url": "https://huggingface.co/baselabs/mammoth-1", "params": "27B (27,356,728,560 by the Hub's safetensors count)", "listing": "https://www.anchorterminal.com/tools/mammoth-1" } ] }, "notable": [ "Published by Baseten's research lab. Baseten's library page (developer Base Labs, licence MIT) links to huggingface.co/baselabs/joey-1, the card links back to Baseten's library page, blog and the Base Labs report, and all four commits are by mkirkby (Max Kirkby, an author of the launch blog). The baselabs organisation is unverified and doesn't name Baseten (https://www.baseten.co/library/joey-1/; https://huggingface.co/api/models/baselabs/joey-1/commits/main)", "Jev Decision Index 0.4.1, a community leaderboard in the personal Space multimodalart/jev-decision-index, unofficial and not affiliated with TypeSafe AI, which ranks by its Full score from private tests and says the public benchmarks don't count. joey-1 was added on 29 October 2026 (PR #330) with a Full score of 35.91, 149th of 247, and a public score of 63.30, 47th of 247. On the public score it's the highest of every model under 4B; on the Full score StartLux-Decision v1.1 2B (40.11, same Qwen3.5-2B base) and Standard One 3B SH (39.79) are above it (https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/main/data/index.json)", "The Decision Index's notes say training includes train splits of Decision Index benchmarks (declared by the author) and that one private new-domain test isn't counted for this model because the index found signs its training data overlapped it. joey-1 scores 10.2 on new domains against 50.16 on same skills (https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/main/data/index.json)", "Baseten's library page says joey-1 'is the top 2B model on the Jev Decision Index 0.4'. The card says 'Best model under 4B on the Jev Decision Index 0.4 public split: 63.30, #37 of 230 models'. The index ranks by the Full score, on which it isn't the top 2B model (https://www.baseten.co/library/joey-1/)", "Speed. Baseten's blog of 29 October 2026 calls joey-1 'our fastest and most affordable decision model, with a P50 latency of 20 ms', '5x faster than comparable decision model models' and about 2.5x faster than elephant-1 (49 ms), on Baseten's production serving with no hardware stated. The Decision Index's own timing on one RTX PRO 6000 with the author's serving gives joey-1 a median of 84.7 ms, 153rd of 247, against 113.7 ms for elephant-1, with 64 models both faster and higher on the Full score (https://www.baseten.co/blog/decisions-for-a-penny-introducing-joey-1/)", "The card gives 62.9 on Base Labs' own replica of the Artificial Analysis Decision Index. Artificial Analysis's page, read on 30 October 2026, doesn't mention joey-1 (https://artificialanalysis.ai/evaluations/artificial-analysis-decision-index)", "A third party's open pull request (#1, 30 October 2026) adds unverified eval results from harness-hub/safeagents-judge-bench, an agent tool-call guardrail benchmark published the same day, run on an NVIDIA L4: balanced accuracy 0.502, AUROC 0.482, false block rate 0.154, category macro F1 0.219 (https://huggingface.co/api/models/baselabs/joey-1?expand[]=evalResults)", "Not a standard Qwen3.5 checkpoint to serve. config.json asks for block-bidirectional attention in the full-attention layers and a slot readout through modeling_overrides, which stock loaders ignore. setup.sh, serve.patch, engine.py and constraints.txt are byte for byte elephant-1's: OmniJev's OneJev runtime at a pinned commit with the patch applied, plus the Decision Index kit (https://huggingface.co/baselabs/joey-1/raw/main/setup.sh)", "67 downloads and 13 likes on 30 October 2026, three days after the repository was created. No quantised build or copy by anyone else was found (https://huggingface.co/api/models/baselabs/joey-1)" ], "area": "models", "details": [ { "label": "Surface graded", "value": "The open weights at huggingface.co/baselabs/joey-1, read from the card and its first version, the files and their metadata, config.json, engine.py, setup.sh, serve.patch, the commits, discussions and eval results, Baseten's library page and launch blog, the Decision Index Space's data and README and Artificial Analysis's index page on 30 October 2026. Nothing was downloaded or run. Baseten's hosted Model API isn't graded here" }, { "label": "Built on", "value": "Qwen/Qwen3.5-2B (Apache-2.0), named in the card's metadata. A full fine-tune of the language model for one epoch (43,390 steps) over the same 6.21M-example Mix 8 as elephant-1, with the vision encoder frozen, per the card. The chat template is byte for byte the base's" }, { "label": "Relation to TypeSafe's Jev", "value": "None by ownership. It answers TypeSafe's System One question types (choice, noul, score), and Baseten serves it at /v1/systemone. The Jev Decision Index that ranks it is a community board in a personal Hugging Face Space that says it isn't affiliated with TypeSafe AI" }, { "label": "Model", "value": "2.72B parameters in BF16 by the Hub's safetensors count (the card says 2B; the Qwen3.5-2B base counts 2.27B), 24 layers in a 3 to 1 mix of Gated DeltaNet and full attention, with the full-attention layers changed to a block-bidirectional mask so the state's cache is shared by every question, and the Qwen3.5 vision encoder. The answer is read from the option letters' logits at each question's slot, up to 256 slots" }, { "label": "Files", "value": "One model.safetensors (5.44 GB, BF16), tokenizer and configs, processor_config.json, chat_template.jinja, readout.json, a banner image and the serving bundle engine.py, setup.sh, serve.patch and constraints.txt. No pickle files. Hugging Face lists a SHA-256 for the LFS files. The weights haven't changed since the upload of 27 October" }, { "label": "Licence", "value": "MIT by the card's metadata, unchanged since the upload, with no LICENSE file and no copyright line. Baseten's library page says MIT and the blog says open weights. The Apache-2.0 base asks for its licence to travel with derivatives, and the repository carries no copy" }, { "label": "Runtimes", "value": "Only OmniJev's OneJev qev runtime at a pinned commit with the repository's serve.patch, through setup.sh. No released vLLM, SGLang, llama.cpp, Ollama or LM Studio route applies the block-bidirectional mask and slot readout, and Transformers loads the qwen3_5 architecture but not those changes" }, { "label": "Context", "value": "config.json keeps the base's 262,144 positions, but the card gives a maximum sequence length of 16,384 tokens and says longer requests are refused, not truncated. Baseten's blog says dedicated deployments unlock the full 262k context window" }, { "label": "Inputs and outputs", "value": "A state (text, optionally with images) and named questions, each choice (named options with descriptions), noul (yes or no, criteria optional) or score (ordered levels, lowest first). All questions share one prefill of the state. It returns P(yes) for noul, and the choice or score with a probability for every option otherwise. The card documents the request, the answer fields and the call in OneJev's qev. No text generation and no thinking" }, { "label": "Hardware", "value": "The card says one CUDA GPU on the pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel image. Trained on 2 nodes of 8 H100. The Decision Index ran it on one RTX PRO 6000. No memory figure from Base Labs" }, { "label": "Training data", "value": "Mix 8, 6.21M decision examples, 58.3% core decision skills, 16.1% safety and abstention, 16.1% judging and expert domains and 9.5% public decision data, per the card, with the rest in the Base Labs report. Not published. No cut-off" } ], "provenance": { "legalEntity": "Baseten Labs, Inc.", "domain": "baseten.co", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-30", "notes": [ "Base Labs is Baseten's research lab (labs.baseten.co). 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 Base Labs report's authors. Baseten's library page and the card link it to Baseten.", "Nothing is hosted under this listing, so the licence stands in for terms of service and no privacy policy is scored.", "No changelog. security.txt is recorded as absent from the elephant-1 check of 21 October 2026 and wasn't re-read." ], "score": 50, "checks": [ { "check": "Legal entity named", "value": "Baseten Labs, Inc.", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "baseten.co, no registry record we could read", "points": 0, "max": 15, "state": "no" }, { "check": "Endpoint on the vendor's domain", "value": "no hosted endpoint", "points": 0, "max": 0, "state": "na" }, { "check": "Terms of service", "value": "nothing hosted, so the 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 licence stands in", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "nothing hosted, not scored", "points": 0, "max": 0, "state": "na" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "People named", "value": "6 named with their role, 6 with a public profile", "points": 10, "max": 10, "state": "ok" }, { "check": "Support route", "value": "a support address, help pages, a community", "points": 5, "max": 5, "state": "ok" } ] }, "humans": { "slug": "joey-1", "checked": "2026-10-30", "company": "Baseten", "people": [ { "name": "Tuhin Srivastava", "role": "Co-founder and CEO", "founder": true, "linkedin": "https://www.linkedin.com/in/tuhin-srivastava/", "page": "/people/tuhin-srivastava/" }, { "name": "Amir Haghighat", "role": "Co-founder and CTO", "founder": true, "linkedin": "https://www.linkedin.com/in/amirhaghighat/", "page": "/people/amir-haghighat/" }, { "name": "Phil Howes", "role": "Co-founder and Chief Scientist", "founder": true, "linkedin": "https://www.linkedin.com/in/philhowes/", "page": "/people/phil-howes/" }, { "name": "Pankaj Gupta", "role": "Co-founder", "founder": true, "linkedin": "https://www.linkedin.com/in/pankajcraft/", "page": "/people/pankaj-gupta/" }, { "name": "Max Kirkby", "role": "Base Labs researcher; joey-1 launch blog co-author", "linkedin": "https://www.linkedin.com/in/max-kirkby15/", "x": "https://x.com/maxkirkby", "page": "/people/max-kirkby/" }, { "name": "Charles O’Neill", "role": "Base Labs researcher; joey-1 launch blog co-author", "x": "https://x.com/oneill_c", "page": "/people/charles-o-neill/" } ], "peopleNote": "Started from data/humans/elephant-1.json (Baseten, checked 28 October 2026). The four founders and their roles are from Baseten's about page as read there and weren't re-read today. Baseten's joey-1 launch blog, read on 30 October 2026, names Max Kirkby and Charles O'Neill as its authors, and all four commits to baselabs/joey-1 are by mkirkby; their LinkedIn and X links are carried from the elephant-1 file. The Base Labs report's other authors (Michael Psenka, Thomas Villeneuve, Aaryam Sharma) aren't named on joey-1's pages, so they're left off. ownership and investors are left out so land.py copies them from the Baseten file; a news search on 30 October 2026 found nothing after the Series F of June 2026.", "companySocial": { "linkedin": "https://www.linkedin.com/company/baseten", "x": "https://x.com/baseten" }, "support": { "emails": [ "support@baseten.co" ], "urls": [ "https://docs.baseten.co/", "https://www.baseten.co/library/joey-1/" ], "community": [ { "label": "Hugging Face model community", "url": "https://huggingface.co/baselabs/joey-1/discussions", "kind": "link" } ] }, "sources": [ "https://www.baseten.co/blog/decisions-for-a-penny-introducing-joey-1/", "https://www.baseten.co/library/joey-1/", "https://huggingface.co/api/models/baselabs/joey-1/commits/main", "https://www.baseten.co/about-us/", "https://huggingface.co/baselabs/joey-1" ], "ownership": { "status": "private", "valuation": { "amount": "$13B", "basis": "stated", "round": "Series F", "asOf": "2026-06", "source": "https://www.baseten.co/blog/announcing-our-series-f/" }, "checked": "2026-10-28", "sources": [ "https://www.baseten.co/blog/announcing-our-series-a/", "https://www.baseten.co/blog/announcing-our-series-b/", "https://www.baseten.co/blog/announcing-baseten-75m-series-c/", "https://www.baseten.co/blog/announcing-baseten-150m-series-d/", "https://www.baseten.co/blog/announcing-baseten-s-300m-series-e/", "https://www.baseten.co/blog/announcing-our-series-f/", "https://www.baseten.co/about-us/" ] }, "investors": [ { "name": "Greylock", "kind": "vc", "rounds": [ "Seed, 2019", "Series A, April 2022", "Series B, March 2024", "Series C, February 2025", "Series D, September 2025", "Series E, January 2026", "Series F, June 2026" ], "lead": true, "url": "https://greylock.com", "source": "https://www.baseten.co/blog/announcing-our-series-a/", "quote": "Our Series A was led by Sarah Guo from Greylock Partners who also co-led our seed round in 2019.", "page": "/investors/greylock/" }, { "name": "IVP", "kind": "vc", "rounds": [ "Series B, March 2024", "Series C, February 2025", "Series D, September 2025", "Series E, January 2026", "Series F, June 2026" ], "lead": true, "url": "https://www.ivp.com", "source": "https://www.baseten.co/blog/announcing-baseten-s-300m-series-e/", "quote": "The round is led by IVP and CapitalG, both doubling down on their investment in Baseten, joined by 01A, Altimeter, Battery Ventures, BOND, BoxGroup, Blackbird Ventures, Conviction, Greylock and NVIDIA.", "page": "/investors/ivp/" }, { "name": "Spark Capital", "kind": "vc", "rounds": [ "Series B, March 2024", "Series C, February 2025", "Series D, September 2025", "Series F, June 2026" ], "lead": true, "url": "https://www.sparkcapital.com", "source": "https://www.baseten.co/blog/announcing-our-series-f/", "quote": "led by Altimeter Capital, Conviction Partners, and Spark Capital, co-led by Sands Capital and Wellington Management, with participation from Battery Ventures, Blackbird, D.E. Shaw Ventures, Durable Capital Partners, Greylock, IVP, Verified Capital, and 01A.", "page": "/investors/spark-capital/" }, { "name": "South Park Commons", "kind": "vc", "rounds": [ "Series A, April 2022", "Series B, March 2024", "Series C, February 2025" ], "url": "https://www.southparkcommons.com", "source": "https://www.baseten.co/blog/announcing-baseten-75m-series-c/", "quote": "The round was co-led by IVP and Spark, with continued participation from Greylock, Conviction, South Park Commons, Basecase and Lachy Groom. We're also excited to welcome Adam Bain and Dick Costolo of 01a as new investors.", "page": "/investors/south-park-commons/" }, { "name": "Caffeinated Capital", "kind": "vc", "rounds": [ "Series A, April 2022" ], "url": "https://www.caffeinated.com", "source": "https://www.baseten.co/blog/announcing-our-series-a/", "quote": "We're also thrilled to have the team at South Park Commons, Lachy Groom, and Ray Tonsing (Caffeinated Capital) invest alongside a group of outstanding angels including", "page": "/investors/caffeinated-capital/" }, { "name": "Lachy Groom", "kind": "angel", "rounds": [ "Series A, April 2022", "Series B, March 2024", "Series C, February 2025" ], "source": "https://www.baseten.co/blog/announcing-our-series-b/", "quote": "IVP and Spark led the round, and our existing investors Greylock, South Park Commons, Lachy Groom, and Base Case also participated.", "page": "/investors/lachy-groom/" }, { "name": "Base Case", "firm": "Basecase Capital", "kind": "vc", "rounds": [ "Series B, March 2024", "Series C, February 2025" ], "url": "https://basecase.vc", "source": "https://www.baseten.co/blog/announcing-our-series-b/", "quote": "IVP and Spark led the round, and our existing investors Greylock, South Park Commons, Lachy Groom, and Base Case also participated.", "page": "/investors/basecase-capital/" }, { "name": "Conviction", "kind": "vc", "rounds": [ "Series C, February 2025", "Series D, September 2025", "Series E, January 2026", "Series F, June 2026" ], "lead": true, "url": "https://www.conviction.com", "source": "https://www.baseten.co/blog/announcing-our-series-f/", "quote": "led by Altimeter Capital, Conviction Partners, and Spark Capital, co-led by Sands Capital and Wellington Management, with participation from Battery Ventures, Blackbird, D.E. Shaw Ventures, Durable Capital Partners, Greylock, IVP, Verified Capital, and 01A.", "page": "/investors/conviction/" }, { "name": "01A", "firm": "01 Advisors", "kind": "vc", "rounds": [ "Series C, February 2025", "Series D, September 2025", "Series E, January 2026", "Series F, June 2026" ], "url": "https://01a.com", "source": "https://www.baseten.co/blog/announcing-baseten-75m-series-c/", "quote": "The round was co-led by IVP and Spark, with continued participation from Greylock, Conviction, South Park Commons, Basecase and Lachy Groom. We're also excited to welcome Adam Bain and Dick Costolo of 01a as new investors.", "page": "/investors/01-advisors/" }, { "name": "BOND", "kind": "vc", "rounds": [ "Series D, September 2025", "Series E, January 2026" ], "lead": true, "url": "https://www.bondcap.com", "source": "https://www.baseten.co/blog/announcing-baseten-150m-series-d/", "quote": "Today, we're excited to announce our $150M Series D, led by BOND, with Jay Simons joining our Board. We're also thrilled to welcome Conviction and CapitalG to the round, alongside support from 01A, IVP, Spark, Greylock, Scribble Ventures, BoxGroup, and Premji Invest.", "page": "/investors/bond/" }, { "name": "CapitalG", "kind": "corporate", "rounds": [ "Series D, September 2025", "Series E, January 2026" ], "lead": true, "url": "https://www.capitalg.com", "source": "https://www.baseten.co/blog/announcing-baseten-s-300m-series-e/", "quote": "The round is led by IVP and CapitalG, both doubling down on their investment in Baseten, joined by 01A, Altimeter, Battery Ventures, BOND, BoxGroup, Blackbird Ventures, Conviction, Greylock and NVIDIA.", "page": "/investors/capitalg/" }, { "name": "Scribble Ventures", "kind": "vc", "rounds": [ "Series D, September 2025" ], "url": "https://www.scribble.vc", "source": "https://www.baseten.co/blog/announcing-baseten-150m-series-d/", "quote": "Today, we're excited to announce our $150M Series D, led by BOND, with Jay Simons joining our Board. We're also thrilled to welcome Conviction and CapitalG to the round, alongside support from 01A, IVP, Spark, Greylock, Scribble Ventures, BoxGroup, and Premji Invest.", "page": "/investors/scribble-ventures/" }, { "name": "BoxGroup", "kind": "vc", "rounds": [ "Series D, September 2025", "Series E, January 2026" ], "url": "https://www.boxgroup.com", "source": "https://www.baseten.co/blog/announcing-baseten-150m-series-d/", "quote": "Today, we're excited to announce our $150M Series D, led by BOND, with Jay Simons joining our Board. We're also thrilled to welcome Conviction and CapitalG to the round, alongside support from 01A, IVP, Spark, Greylock, Scribble Ventures, BoxGroup, and Premji Invest.", "page": "/investors/boxgroup/" }, { "name": "Premji Invest", "kind": "vc", "rounds": [ "Series D, September 2025" ], "url": "https://www.premjiinvest.com", "source": "https://www.baseten.co/blog/announcing-baseten-150m-series-d/", "quote": "Today, we're excited to announce our $150M Series D, led by BOND, with Jay Simons joining our Board. We're also thrilled to welcome Conviction and CapitalG to the round, alongside support from 01A, IVP, Spark, Greylock, Scribble Ventures, BoxGroup, and Premji Invest.", "page": "/investors/premji-invest/" }, { "name": "Altimeter", "firm": "Altimeter Capital", "kind": "vc", "rounds": [ "Series E, January 2026", "Series F, June 2026" ], "lead": true, "url": "https://www.altimeter.com", "source": "https://www.baseten.co/blog/announcing-our-series-f/", "quote": "led by Altimeter Capital, Conviction Partners, and Spark Capital, co-led by Sands Capital and Wellington Management, with participation from Battery Ventures, Blackbird, D.E. Shaw Ventures, Durable Capital Partners, Greylock, IVP, Verified Capital, and 01A.", "page": "/investors/altimeter-capital/" }, { "name": "Battery Ventures", "kind": "vc", "rounds": [ "Series E, January 2026", "Series F, June 2026" ], "url": "https://www.battery.com", "source": "https://www.baseten.co/blog/announcing-our-series-f/", "quote": "led by Altimeter Capital, Conviction Partners, and Spark Capital, co-led by Sands Capital and Wellington Management, with participation from Battery Ventures, Blackbird, D.E. Shaw Ventures, Durable Capital Partners, Greylock, IVP, Verified Capital, and 01A.", "page": "/investors/battery-ventures/" }, { "name": "Blackbird Ventures", "kind": "vc", "rounds": [ "Series E, January 2026", "Series F, June 2026" ], "url": "https://www.blackbird.vc", "source": "https://www.baseten.co/blog/announcing-baseten-s-300m-series-e/", "quote": "The round is led by IVP and CapitalG, both doubling down on their investment in Baseten, joined by 01A, Altimeter, Battery Ventures, BOND, BoxGroup, Blackbird Ventures, Conviction, Greylock and NVIDIA.", "page": "/investors/blackbird-ventures/" }, { "name": "NVIDIA", "kind": "corporate", "rounds": [ "Series E, January 2026" ], "url": "https://www.nvidia.com", "source": "https://www.baseten.co/blog/announcing-baseten-s-300m-series-e/", "quote": "The round is led by IVP and CapitalG, both doubling down on their investment in Baseten, joined by 01A, Altimeter, Battery Ventures, BOND, BoxGroup, Blackbird Ventures, Conviction, Greylock and NVIDIA.", "page": "/investors/nvidia/" }, { "name": "Sands Capital", "kind": "vc", "rounds": [ "Series F, June 2026" ], "lead": true, "url": "https://www.sandscapital.com", "source": "https://www.baseten.co/blog/announcing-our-series-f/", "quote": "led by Altimeter Capital, Conviction Partners, and Spark Capital, co-led by Sands Capital and Wellington Management, with participation from Battery Ventures, Blackbird, D.E. Shaw Ventures, Durable Capital Partners, Greylock, IVP, Verified Capital, and 01A.", "page": "/investors/sands-capital/" }, { "name": "Wellington Management", "kind": "vc", "rounds": [ "Series F, June 2026" ], "lead": true, "url": "https://www.wellington.com", "source": "https://www.baseten.co/blog/announcing-our-series-f/", "quote": "led by Altimeter Capital, Conviction Partners, and Spark Capital, co-led by Sands Capital and Wellington Management, with participation from Battery Ventures, Blackbird, D.E. Shaw Ventures, Durable Capital Partners, Greylock, IVP, Verified Capital, and 01A.", "page": "/investors/wellington-management/" }, { "name": "D.E. Shaw Ventures", "firm": "D. E. Shaw Ventures", "kind": "vc", "rounds": [ "Series F, June 2026" ], "url": "https://www.deshaw.com", "source": "https://www.baseten.co/blog/announcing-our-series-f/", "quote": "led by Altimeter Capital, Conviction Partners, and Spark Capital, co-led by Sands Capital and Wellington Management, with participation from Battery Ventures, Blackbird, D.E. Shaw Ventures, Durable Capital Partners, Greylock, IVP, Verified Capital, and 01A.", "page": "/investors/d-e-shaw-ventures/" }, { "name": "Durable Capital Partners", "kind": "vc", "rounds": [ "Series F, June 2026" ], "url": "https://www.durablecap.com", "source": "https://www.baseten.co/blog/announcing-our-series-f/", "quote": "led by Altimeter Capital, Conviction Partners, and Spark Capital, co-led by Sands Capital and Wellington Management, with participation from Battery Ventures, Blackbird, D.E. Shaw Ventures, Durable Capital Partners, Greylock, IVP, Verified Capital, and 01A.", "page": "/investors/durable-capital-partners/" }, { "name": "Verified Capital", "kind": "vc", "rounds": [ "Series F, June 2026" ], "source": "https://www.baseten.co/blog/announcing-our-series-f/", "quote": "led by Altimeter Capital, Conviction Partners, and Spark Capital, co-led by Sands Capital and Wellington Management, with participation from Battery Ventures, Blackbird, D.E. Shaw Ventures, Durable Capital Partners, Greylock, IVP, Verified Capital, and 01A.", "page": "/investors/verified-capital/" }, { "name": "Greg Brockman", "kind": "angel", "rounds": [ "Series A, April 2022" ], "source": "https://www.baseten.co/blog/announcing-our-series-a/", "quote": "a group of outstanding angels including Greg Brockman, Dylan Field, Pascal Levy-Garboua, Mustafa Suleyman, DJ Patil, Dev Ittycheria, Jay Simons, Jean-Denis Greze, Peter Skomoroch, Sandy Kory, Alana Anderson, and Cristina Cordova.", "page": "/investors/greg-brockman/" }, { "name": "Dylan Field", "kind": "angel", "rounds": [ "Series A, April 2022" ], "source": "https://www.baseten.co/blog/announcing-our-series-a/", "quote": "a group of outstanding angels including Greg Brockman, Dylan Field, Pascal Levy-Garboua, Mustafa Suleyman, DJ Patil, Dev Ittycheria, Jay Simons, Jean-Denis Greze, Peter Skomoroch, Sandy Kory, Alana Anderson, and Cristina Cordova.", "page": "/investors/dylan-field/" }, { "name": "Pascal Levy-Garboua", "kind": "angel", "rounds": [ "Series A, April 2022" ], "source": "https://www.baseten.co/blog/announcing-our-series-a/", "quote": "a group of outstanding angels including Greg Brockman, Dylan Field, Pascal Levy-Garboua, Mustafa Suleyman, DJ Patil, Dev Ittycheria, Jay Simons, Jean-Denis Greze, Peter Skomoroch, Sandy Kory, Alana Anderson, and Cristina Cordova.", "page": "/investors/pascal-levy-garboua/" }, { "name": "Mustafa Suleyman", "kind": "angel", "rounds": [ "Series A, April 2022" ], "source": "https://www.baseten.co/blog/announcing-our-series-a/", "quote": "a group of outstanding angels including Greg Brockman, Dylan Field, Pascal Levy-Garboua, Mustafa Suleyman, DJ Patil, Dev Ittycheria, Jay Simons, Jean-Denis Greze, Peter Skomoroch, Sandy Kory, Alana Anderson, and Cristina Cordova.", "page": "/investors/mustafa-suleyman/" }, { "name": "DJ Patil", "kind": "angel", "rounds": [ "Series A, April 2022" ], "source": "https://www.baseten.co/blog/announcing-our-series-a/", "quote": "a group of outstanding angels including Greg Brockman, Dylan Field, Pascal Levy-Garboua, Mustafa Suleyman, DJ Patil, Dev Ittycheria, Jay Simons, Jean-Denis Greze, Peter Skomoroch, Sandy Kory, Alana Anderson, and Cristina Cordova.", "page": "/investors/dj-patil/" }, { "name": "Dev Ittycheria", "kind": "angel", "rounds": [ "Series A, April 2022" ], "source": "https://www.baseten.co/blog/announcing-our-series-a/", "quote": "a group of outstanding angels including Greg Brockman, Dylan Field, Pascal Levy-Garboua, Mustafa Suleyman, DJ Patil, Dev Ittycheria, Jay Simons, Jean-Denis Greze, Peter Skomoroch, Sandy Kory, Alana Anderson, and Cristina Cordova.", "page": "/investors/dev-ittycheria/" }, { "name": "Jay Simons", "kind": "angel", "rounds": [ "Series A, April 2022" ], "source": "https://www.baseten.co/blog/announcing-our-series-a/", "quote": "a group of outstanding angels including Greg Brockman, Dylan Field, Pascal Levy-Garboua, Mustafa Suleyman, DJ Patil, Dev Ittycheria, Jay Simons, Jean-Denis Greze, Peter Skomoroch, Sandy Kory, Alana Anderson, and Cristina Cordova.", "page": "/investors/jay-simons/" }, { "name": "Jean-Denis Greze", "kind": "angel", "rounds": [ "Series A, April 2022" ], "source": "https://www.baseten.co/blog/announcing-our-series-a/", "quote": "a group of outstanding angels including Greg Brockman, Dylan Field, Pascal Levy-Garboua, Mustafa Suleyman, DJ Patil, Dev Ittycheria, Jay Simons, Jean-Denis Greze, Peter Skomoroch, Sandy Kory, Alana Anderson, and Cristina Cordova.", "page": "/investors/jean-denis-greze/" }, { "name": "Peter Skomoroch", "kind": "angel", "rounds": [ "Series A, April 2022" ], "source": "https://www.baseten.co/blog/announcing-our-series-a/", "quote": "a group of outstanding angels including Greg Brockman, Dylan Field, Pascal Levy-Garboua, Mustafa Suleyman, DJ Patil, Dev Ittycheria, Jay Simons, Jean-Denis Greze, Peter Skomoroch, Sandy Kory, Alana Anderson, and Cristina Cordova.", "page": "/investors/peter-skomoroch/" }, { "name": "Sandy Kory", "kind": "angel", "rounds": [ "Series A, April 2022" ], "source": "https://www.baseten.co/blog/announcing-our-series-a/", "quote": "a group of outstanding angels including Greg Brockman, Dylan Field, Pascal Levy-Garboua, Mustafa Suleyman, DJ Patil, Dev Ittycheria, Jay Simons, Jean-Denis Greze, Peter Skomoroch, Sandy Kory, Alana Anderson, and Cristina Cordova.", "page": "/investors/sandy-kory/" }, { "name": "Alana Anderson", "kind": "angel", "rounds": [ "Series A, April 2022" ], "source": "https://www.baseten.co/blog/announcing-our-series-a/", "quote": "a group of outstanding angels including Greg Brockman, Dylan Field, Pascal Levy-Garboua, Mustafa Suleyman, DJ Patil, Dev Ittycheria, Jay Simons, Jean-Denis Greze, Peter Skomoroch, Sandy Kory, Alana Anderson, and Cristina Cordova.", "page": "/investors/alana-anderson/" }, { "name": "Cristina Cordova", "kind": "angel", "rounds": [ "Series A, April 2022" ], "source": "https://www.baseten.co/blog/announcing-our-series-a/", "quote": "a group of outstanding angels including Greg Brockman, Dylan Field, Pascal Levy-Garboua, Mustafa Suleyman, DJ Patil, Dev Ittycheria, Jay Simons, Jean-Denis Greze, Peter Skomoroch, Sandy Kory, Alana Anderson, and Cristina Cordova.", "page": "/investors/cristina-cordova/" } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/joey-1.json" }, "verify": { "accepts": "a page on baseten.co or one of its subdomains", "badgeUrl": "https://www.anchorterminal.com/badges/joey-1.svg", "body": { "slug": "joey-1", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/joey-1", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/joey-1\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/joey-1.svg\" alt=\"joey-1 on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![joey-1 on Anchor Terminal](https://www.anchorterminal.com/badges/joey-1.svg)](https://www.anchorterminal.com/tools/joey-1)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/joey-1\"\u003ejoey-1 on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/joey-1", "json": "https://www.anchorterminal.com/tools/joey-1.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/joey-1.md", "mcp": "https://www.anchorterminal.com/mcp", "pricing": "https://www.anchorterminal.com/tools/joey-1#pricing", "reviews": "https://www.anchorterminal.com/tools/joey-1#reviews", "slim": "https://www.anchorterminal.com/tools/joey-1.min.md" }, "markdown": "## Overview\n\n**Grade C · 57.1/100 · rank #78 of 117 open-weight models · #16 in Decision models · not agent-ready · confidence low**\n\n\nMore from Baseten, listed separately because each is its own product: [Baseten](https://www.anchorterminal.com/tools/baseten.md) (GPU \u0026 serverless compute), [elephant-1](https://www.anchorterminal.com/tools/elephant-1.md) (Decision models), [mammoth-1](https://www.anchorterminal.com/tools/mammoth-1.md) (Decision models).\n\nTrained by Base Labs (Baseten), in the Base Labs decision models (-1) family, with [elephant-1](https://www.anchorterminal.com/tools/elephant-1.md), [mammoth-1](https://www.anchorterminal.com/tools/mammoth-1.md). Every model from this lab and its older versions: https://www.anchorterminal.com/open-weights/#baselabs.\n\n## Assessment\n\nA 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.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | Baseten (https://labs.baseten.co) |\n| Kind | Open-weight model |\n| Category | Decision models (https://www.anchorterminal.com/categories/decision-models) |\n| Auth | None · The weights download from Hugging Face with no account, token or terms to accept. The repository is not gated (checked 2026-10-30). Baseten's hosted Model API for the same model needs a Baseten API key. |\n| Pricing | Free (Free) · Free to download under the MIT licence the card's metadata names. Running it costs the hardware, 5.47 GB of BF16 files by the Hub's file list. Baseten also serves it on its Model APIs as decision-models/baseten-joey-2b-latest at $0.01 per million input tokens, with cached input and output at $0.00, per its library page (checked 2026-10-30). |\n| x402 | No · Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-10-30). |\n| Licence | 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 |\n| Packages | huggingface: `baselabs/joey-1` |\n| Source | https://huggingface.co/baselabs/joey-1 |\n| Docs | https://huggingface.co/baselabs/joey-1 |\n| llms.txt | not found |\n| Last release | 2026-10-29 |\n| Surface graded | The open weights at huggingface.co/baselabs/joey-1, read from the card and its first version, the files and their metadata, config.json, engine.py, setup.sh, serve.patch, the commits, discussions and eval results, Baseten's library page and launch blog, the Decision Index Space's data and README and Artificial Analysis's index page on 30 October 2026. Nothing was downloaded or run. Baseten's hosted Model API isn't graded here |\n| Built on | Qwen/Qwen3.5-2B (Apache-2.0), named in the card's metadata. A full fine-tune of the language model for one epoch (43,390 steps) over the same 6.21M-example Mix 8 as elephant-1, with the vision encoder frozen, per the card. The chat template is byte for byte the base's |\n| Relation to TypeSafe's Jev | None by ownership. It answers TypeSafe's System One question types (choice, noul, score), and Baseten serves it at /v1/systemone. The Jev Decision Index that ranks it is a community board in a personal Hugging Face Space that says it isn't affiliated with TypeSafe AI |\n| Model | 2.72B parameters in BF16 by the Hub's safetensors count (the card says 2B; the Qwen3.5-2B base counts 2.27B), 24 layers in a 3 to 1 mix of Gated DeltaNet and full attention, with the full-attention layers changed to a block-bidirectional mask so the state's cache is shared by every question, and the Qwen3.5 vision encoder. The answer is read from the option letters' logits at each question's slot, up to 256 slots |\n| Files | One model.safetensors (5.44 GB, BF16), tokenizer and configs, processor_config.json, chat_template.jinja, readout.json, a banner image and the serving bundle engine.py, setup.sh, serve.patch and constraints.txt. No pickle files. Hugging Face lists a SHA-256 for the LFS files. The weights haven't changed since the upload of 27 October |\n| Licence | MIT by the card's metadata, unchanged since the upload, with no LICENSE file and no copyright line. Baseten's library page says MIT and the blog says open weights. The Apache-2.0 base asks for its licence to travel with derivatives, and the repository carries no copy |\n| Runtimes | Only OmniJev's OneJev qev runtime at a pinned commit with the repository's serve.patch, through setup.sh. No released vLLM, SGLang, llama.cpp, Ollama or LM Studio route applies the block-bidirectional mask and slot readout, and Transformers loads the qwen3_5 architecture but not those changes |\n| Context | config.json keeps the base's 262,144 positions, but the card gives a maximum sequence length of 16,384 tokens and says longer requests are refused, not truncated. Baseten's blog says dedicated deployments unlock the full 262k context window |\n| Inputs and outputs | A state (text, optionally with images) and named questions, each choice (named options with descriptions), noul (yes or no, criteria optional) or score (ordered levels, lowest first). All questions share one prefill of the state. It returns P(yes) for noul, and the choice or score with a probability for every option otherwise. The card documents the request, the answer fields and the call in OneJev's qev. No text generation and no thinking |\n| Hardware | The card says one CUDA GPU on the pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel image. Trained on 2 nodes of 8 H100. The Decision Index ran it on one RTX PRO 6000. No memory figure from Base Labs |\n| Training data | Mix 8, 6.21M decision examples, 58.3% core decision skills, 16.1% safety and abstention, 16.1% judging and expert domains and 9.5% public decision data, per the card, with the rest in the Base Labs report. Not published. No cut-off |\n| Capabilities | inference.decision, model.open-weights |\n| Tags | open-weights, model, decision-model, full-fine-tune, calibrated-probabilities, vision, mit, safetensors, self-hosted |\n| JSON | https://www.anchorterminal.com/api/v1/tools/joey-1.json |\n\n## Score breakdown (methodology v0.7, October 2026 research run)\n\nAssessed 2026-10-30 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: low. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Capability | 35% | pending | pending | n/a |\n| Reach | 25% | 38.5 | 60 | 23.1 |\n| Risk | 20% | 30.8 | 55 | 16.9 |\n| Agent interface | 10% | 15.4 | 70 | 10.8 |\n| Documentation and upkeep | 10% | 15.4 | 54 | 8.3 |\n| Negative events | up to −15 | up to −15 | 29 October 2026. Baseten's library page says 'On release (October 2026), joey-1 is the top 2B model on the Jev Decision Index 0.4.' The index (edition 0.4.1, joey-1 added 29 October in PR #330) ranks by its Full score and says the public benchmarks don't count. On it joey-1 has 35.91, 149th of 247, below StartLux-Decision v1.1 2B at 40.11 on the same Qwen3.5-2B base. Only the public score (63.30, first of the models under 4B) supports the claim, and the card names that split while the library page doesn't. Sources: https://www.baseten.co/library/joey-1/ and https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/main/data/index.json (-2) | -2 |\n| **Total** | | | | **57.1 → C** |\n\n### Why each score\n\n- Capability: Pending for this listing. Nobody independent has published results for it in at least two areas yet, so its weight is shared across the other four and the total is capped at 61 until they do or our own runs start.\n- Reach 60 (checked 2026-10-30): Memory 30 of 30, the BF16 repository is 5.47 GB, 6.6 GB with a fifth added, so it fits 8 GB. Runtimes 0, only a third party's OneJev runtime patched by the repository's serve.patch applies the model's changed attention and readout. Builds 0, no quantised build. Terms 15, MIT in the card's metadata with nothing added, though there's no licence file. Download 10, not gated. Hosted 5, Baseten's own Model API serves it.\n- Risk 55 (checked 2026-10-30): File safety 15 of 25, safetensors only, but serving it means running the repository's setup.sh and patch. Provenance 15, the organisation Baseten links to, with a checksum on every file. Safety evaluation 0, none for the model; a guardrail benchmark in an open pull request measures task accuracy. Agent guidance 5, abstention and threshold advice only. Licence risk 15, MIT unchanged since upload. Security programme 5, Baseten's disclosure address but no public advisories.\n- Agent interface 70 (checked 2026-10-30): Read as a decision model, by what it takes and returns. Chat template 10 of 20, the base's template is there but the decision prompt is built in code. Tool-calling format 25, the card documents the request, the answer fields and the call in OneJev's qev. Trained tool calling 20, several questions per request from one prefill. Structured output 15, how to ask for each typed answer and what comes back. Reasoning control 0, it doesn't think. Context 0, trained at 16,384 tokens and refused beyond.\n- Documentation and upkeep 54 (checked 2026-10-30): Model card 14 of 20, five of the seven items, no limitations or cut-off. Training data 5, the mix described with no data published and no cut-off. Last change 20, the card changed on 29 October. Responsiveness 0, nobody has asked anything yet. Version policy 5, a first release. File health 10, the files and card agree.\n\nFix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (15 items): https://www.anchorterminal.com/fixes/joey-1.md (JSON https://www.anchorterminal.com/fixes/joey-1.json)\n\n### What we couldn't check\n\n- Whether OneJev's qev after setup.sh serves this checkpoint as trained couldn't be checked without running it. The Decision Index's agreement check (99.60 per cent on 831 rows) suggests it does\n- The deduction rests on the index ranking by its Full score. If the founder reads the library page's 'top 2B model' as meaning the public split the card names, it lapses\n- The 'fastest decision model available' wording in the launch post wasn't found on a Baseten page. The blog says 'our fastest' and '5x faster than comparable decision models' at a 20 ms P50 on Baseten's production serving, which nobody else has measured. The index's own timing on one RTX PRO 6000 puts joey-1 153rd of 247 by median latency\n- Baseten's decision-models doc, its trust centre and security.txt weren't re-read today (the robots.txt reads for www.baseten.co, docs.baseten.co and artificialanalysis.ai were refused in this session), so agent guidance and the security programme rest on the 21 October and 30 September checks\n- The Hub counts 2.72B parameters, about 0.45B more than the Qwen3.5-2B base's 2.27B, and the card doesn't say why\n- The card's 'joey-1 #37 of 230' on the public split doesn't match the index's public rank today (47th of 247)\n\n### Sources\n\n- model card, read 30 October 2026: \u003chttps://huggingface.co/baselabs/joey-1\u003e (seen 2026-10-30)\n- the card as uploaded on 27 October 2026, MIT from the start: \u003chttps://huggingface.co/baselabs/joey-1/raw/3903da0d1252277671a0865daeec29c1965f1cb5/README.md\u003e (seen 2026-10-30)\n- Hub API, card data, gating, downloads, providers, parameter count: \u003chttps://huggingface.co/api/models/baselabs/joey-1\u003e (seen 2026-10-30)\n- eval results from the open pull request #1, safeagents judge bench: \u003chttps://huggingface.co/api/models/baselabs/joey-1?expand[]=evalResults\u003e (seen 2026-10-30)\n- file tree with sizes and SHA-256 for LFS files: \u003chttps://huggingface.co/api/models/baselabs/joey-1/tree/main?recursive=true\u003e (seen 2026-10-30)\n- commit history: \u003chttps://huggingface.co/api/models/baselabs/joey-1/commits/main\u003e (seen 2026-10-30)\n- config, modeling_overrides, positions: \u003chttps://huggingface.co/baselabs/joey-1/raw/main/config.json\u003e (seen 2026-10-30)\n- Decision Index engine, request and answer fields, length refusal: \u003chttps://huggingface.co/baselabs/joey-1/raw/main/engine.py\u003e (seen 2026-10-30)\n- serving setup, OneJev and kit at pinned commits: \u003chttps://huggingface.co/baselabs/joey-1/raw/main/setup.sh\u003e (seen 2026-10-30)\n- patch to OneJev's engine, prompt and readout, same blob as elephant-1's: \u003chttps://huggingface.co/baselabs/joey-1/raw/main/serve.patch\u003e (seen 2026-10-30)\n- base file tree, licence and chat template hash compared: \u003chttps://huggingface.co/api/models/Qwen/Qwen3.5-2B/tree/main?recursive=true\u003e (seen 2026-10-30)\n- organisation members: \u003chttps://huggingface.co/api/organizations/baselabs/members\u003e (seen 2026-10-30)\n- baselabs datasets, joey-1-decision-index gated manually: \u003chttps://huggingface.co/api/datasets?author=baselabs\u003e (seen 2026-10-30)\n- discussions, authors and dates counted by script, no text read: \u003chttps://huggingface.co/baselabs/joey-1/discussions\u003e (seen 2026-10-30)\n- Baseten library page, developer Base Labs, MIT, link to the repository, price, model slug, the top-2B claim: \u003chttps://www.baseten.co/library/joey-1/\u003e (seen 2026-10-30)\n- launch blog of 29 October 2026, speed and price claims, availability: \u003chttps://www.baseten.co/blog/decisions-for-a-penny-introducing-joey-1/\u003e (seen 2026-10-30)\n- Jev Decision Index 0.4.1 data, generated 29 October 2026, joey-1's scores, ranks, latency and notes: \u003chttps://huggingface.co/spaces/multimodalart/jev-decision-index/blob/main/data/index.json\u003e (seen 2026-10-30)\n- Decision Index README, ranked by the Full score, unofficial, not affiliated with TypeSafe AI: \u003chttps://huggingface.co/spaces/multimodalart/jev-decision-index/blob/main/README.md\u003e (seen 2026-10-30)\n- Artificial Analysis Decision Index page, no joey-1 entry found: \u003chttps://artificialanalysis.ai/evaluations/artificial-analysis-decision-index\u003e (seen 2026-10-30)\n- the guardrail benchmark in pull request #1, created 30 October 2026: \u003chttps://huggingface.co/datasets/harness-hub/safeagents-judge-bench\u003e (seen 2026-10-30)\n\n## Score history\n\nEvery move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/joey-1/history.json\n\n- 2026-10-30: graded 57.1 C (methodology 0.7)\n\n## Who's behind it (provenance 50/100, checked 2026-10-30)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | Baseten Labs, Inc. | 20/20 |\n| Domain age | baseten.co, no registry record we could read | 0/15 |\n| Endpoint on the vendor's domain | no hosted endpoint | n/a |\n| Terms of service | nothing hosted, so the 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 licence stands in | 10/10 |\n| Privacy policy | nothing hosted, not scored | n/a |\n| Status page | not found | 0/10 |\n| Changelog | not found | 0/10 |\n| security.txt | not found | 0/10 |\n| People named | 6 named with their role, 6 with a public profile | 10/10 |\n| Support route | a support address, help pages, a community | 5/5 |\n\nBase Labs is Baseten's research lab (labs.baseten.co). The legal entity is from the baseten listing's check of Baseten's terms on 30 September 2026.\n\nThe baselabs Hugging Face organisation is unverified, with nine members, among them the Base Labs report's authors. Baseten's library page and the card link it to Baseten.\n\nNothing is hosted under this listing, so the licence stands in for terms of service and no privacy policy is scored.\n\nNo changelog. security.txt is recorded as absent from the elephant-1 check of 21 October 2026 and wasn't re-read.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service**. Nothing is hosted by the vendor, so there are no terms of service to read. The 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 licence stands in and the check scores in full.\n\n\n**Privacy policy**. Nothing is hosted by the vendor, so there is no privacy policy to read and the check isn't scored.\n\n\n## Humans behind the project (researched 2026-10-30 from public pages, not part of the grade)\n\n### Key people\n\n- Tuhin Srivastava, Co-founder and CEO. LinkedIn: https://www.linkedin.com/in/tuhin-srivastava/\n- Amir Haghighat, Co-founder and CTO. LinkedIn: https://www.linkedin.com/in/amirhaghighat/\n- Phil Howes, Co-founder and Chief Scientist. LinkedIn: https://www.linkedin.com/in/philhowes/\n- Pankaj Gupta, Co-founder. LinkedIn: https://www.linkedin.com/in/pankajcraft/\n- Max Kirkby, Base Labs researcher; joey-1 launch blog co-author. LinkedIn: https://www.linkedin.com/in/max-kirkby15/. X: https://x.com/maxkirkby\n- Charles O’Neill, Base Labs researcher; joey-1 launch blog co-author. X: https://x.com/oneill_c\n- Note: started from data/humans/elephant-1.json (baseten, checked 28 october 2026). the four founders and their roles are from baseten's about page as read there and weren't re-read today. baseten's joey-1 launch blog, read on 30 october 2026, names max kirkby and charles o'neill as its authors, and all four commits to baselabs/joey-1 are by mkirkby; their linkedin and x links are carried from the elephant-1 file. the base labs report's other authors (michael psenka, thomas villeneuve, aaryam sharma) aren't named on joey-1's pages, so they're left off. ownership and investors are left out so land.py copies them from the baseten file; a news search on 30 october 2026 found nothing after the series f of june 2026.\n- Baseten: LinkedIn https://www.linkedin.com/company/baseten X https://x.com/baseten\n\n### Ownership and investors\n\n- Valuation: $13B as announced (the source doesn't say pre- or post-money), Series F, June 2026 (source https://www.baseten.co/blog/announcing-our-series-f/)\n- Backed by: Greylock, IVP, Spark Capital, South Park Commons, Caffeinated Capital, Lachy Groom, Basecase Capital, Conviction, 01 Advisors, BOND, CapitalG, Scribble Ventures, BoxGroup, Premji Invest, Altimeter Capital, Battery Ventures, Blackbird Ventures, NVIDIA, Sands Capital, Wellington Management, D. E. Shaw Ventures, Durable Capital Partners, Verified Capital, Greg Brockman, Dylan Field, Pascal Levy-Garboua, Mustafa Suleyman, DJ Patil, Dev Ittycheria, Jay Simons, Jean-Denis Greze, Peter Skomoroch, Sandy Kory, Alana Anderson, Cristina Cordova\n\n### Getting support\n\n- Support email: support@baseten.co\n- Help: https://docs.baseten.co/\n- Help: https://www.baseten.co/library/joey-1/\n- Community (Hugging Face model community): https://huggingface.co/baselabs/joey-1/discussions\n- Sources: https://www.baseten.co/blog/decisions-for-a-penny-introducing-joey-1/, https://www.baseten.co/library/joey-1/, https://huggingface.co/api/models/baselabs/joey-1/commits/main, https://www.baseten.co/about-us/, https://huggingface.co/baselabs/joey-1\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\nNo hosted version of these weights has a price on OpenRouter, so what a task costs is your own hardware and power.\n\n## Strengths\n\n- Probabilities for choice, yes or no and score questions, several per request from one shared prefill, over text and images\n- 5.5 GB in BF16, so it fits an 8 GB GPU\n- Highest public score of every model under 4B on the Jev Decision Index 0.4.1 at 63.30\n- The card documents the request, answer fields and a runnable call, and the licence has been MIT since upload\n- Not gated, and Baseten's own Model API serves the same model at $0.01 per million input tokens\n\n## Weaknesses\n\n- Serving it needs OneJev at a pinned commit plus the repository's serve.patch, with no released runtime support\n- Full score 35.91 on the Decision Index's private tests, 10.2 on new domains, with one test excluded for signs of training overlap\n- Trained at 16,384 tokens, and longer requests are refused\n- No quantised build, no safety results and no prompt-injection guidance\n- No LICENSE file, and the Apache-2.0 base's licence isn't carried\n\n\n\n## Before you call it (notes for agents)\n\n1. 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 \u0026\u0026 bash joey-1/setup.sh`, which clones OneJev at 81ce62f, applies serve.patch and installs the Decision Index kit\n2. Then call `DecisionEngine(\"baselabs/joey-1\", device=\"cuda:0\").decide(SystemOneRequest(state=..., questions=...))` from qev, as the card shows\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. Expect weaker answers on domains unlike its training mix, and threshold on the returned probability before acting\n6. Without hardware, Baseten's /v1/systemone serves it as decision-models/baseten-joey-2b-latest with a Baseten key\n\n## Get started\n\nInstall:\n\n```bash\nhf download baselabs/joey-1 --local-dir joey-1 \u0026\u0026 bash joey-1/setup.sh # clones OneJev at 81ce62f, applies serve.patch, installs the Decision Index kit (CUDA image pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel)\n# then, in Python:\nfrom qev.engine import DecisionEngine\nfrom qev.schema import SystemOneRequest\nengine = DecisionEngine(\"baselabs/joey-1\", device=\"cuda:0\")\nresp, _ = engine.decide(SystemOneRequest(state=..., questions={...}))\n```\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| JEV-27B-VL | C | 59.5 | open-weight #66 | inference.decision, model.open-weights | no | https://www.anchorterminal.com/tools/jev-27b-vl.md |\n| mammoth-1 | D | 47.7 | open-weight #112 | inference.decision, model.open-weights | no | https://www.anchorterminal.com/tools/mammoth-1.md |\n| elephant-1 | D | 47.6 | open-weight #113 | inference.decision, model.open-weights | no | https://www.anchorterminal.com/tools/elephant-1.md |\n| Qwen3-Embedding-8B | BB | 74.7 | open-weight #1 | model.open-weights | no | https://www.anchorterminal.com/tools/qwen3-embedding-8b.md |\n| Gemma 4 31B IT | BB | 74.1 | open-weight #2 | model.open-weights | no | https://www.anchorterminal.com/tools/gemma-4-31b-it.md |\n| OpenAI Decisions API | BB | 73.1 | 99 | inference.decision | no | https://www.anchorterminal.com/tools/openai-decisions-api.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- Published by Baseten's research lab. Baseten's library page (developer Base Labs, licence MIT) links to huggingface.co/baselabs/joey-1, the card links back to Baseten's library page, blog and the Base Labs report, and all four commits are by mkirkby (Max Kirkby, an author of the launch blog). The baselabs organisation is unverified and doesn't name Baseten (source: \u003chttps://www.baseten.co/library/joey-1/\u003e, \u003chttps://huggingface.co/api/models/baselabs/joey-1/commits/main\u003e)\n- Jev Decision Index 0.4.1, a community leaderboard in the personal Space multimodalart/jev-decision-index, unofficial and not affiliated with TypeSafe AI, which ranks by its Full score from private tests and says the public benchmarks don't count. joey-1 was added on 29 October 2026 (PR #330) with a Full score of 35.91, 149th of 247, and a public score of 63.30, 47th of 247. On the public score it's the highest of every model under 4B; on the Full score StartLux-Decision v1.1 2B (40.11, same Qwen3.5-2B base) and Standard One 3B SH (39.79) are above it (source: \u003chttps://huggingface.co/spaces/multimodalart/jev-decision-index/blob/main/data/index.json\u003e)\n- The Decision Index's notes say training includes train splits of Decision Index benchmarks (declared by the author) and that one private new-domain test isn't counted for this model because the index found signs its training data overlapped it. joey-1 scores 10.2 on new domains against 50.16 on same skills (source: \u003chttps://huggingface.co/spaces/multimodalart/jev-decision-index/blob/main/data/index.json\u003e)\n- Baseten's library page says joey-1 'is the top 2B model on the Jev Decision Index 0.4'. The card says 'Best model under 4B on the Jev Decision Index 0.4 public split: 63.30, #37 of 230 models'. The index ranks by the Full score, on which it isn't the top 2B model (source: \u003chttps://www.baseten.co/library/joey-1/\u003e)\n- Speed. Baseten's blog of 29 October 2026 calls joey-1 'our fastest and most affordable decision model, with a P50 latency of 20 ms', '5x faster than comparable decision model models' and about 2.5x faster than elephant-1 (49 ms), on Baseten's production serving with no hardware stated. The Decision Index's own timing on one RTX PRO 6000 with the author's serving gives joey-1 a median of 84.7 ms, 153rd of 247, against 113.7 ms for elephant-1, with 64 models both faster and higher on the Full score (source: \u003chttps://www.baseten.co/blog/decisions-for-a-penny-introducing-joey-1/\u003e)\n- The card gives 62.9 on Base Labs' own replica of the Artificial Analysis Decision Index. Artificial Analysis's page, read on 30 October 2026, doesn't mention joey-1 (source: \u003chttps://artificialanalysis.ai/evaluations/artificial-analysis-decision-index\u003e)\n- A third party's open pull request (#1, 30 October 2026) adds unverified eval results from harness-hub/safeagents-judge-bench, an agent tool-call guardrail benchmark published the same day, run on an NVIDIA L4: balanced accuracy 0.502, AUROC 0.482, false block rate 0.154, category macro F1 0.219 (source: \u003chttps://huggingface.co/api/models/baselabs/joey-1?expand[]=evalResults\u003e)\n- Not a standard Qwen3.5 checkpoint to serve. config.json asks for block-bidirectional attention in the full-attention layers and a slot readout through modeling_overrides, which stock loaders ignore. setup.sh, serve.patch, engine.py and constraints.txt are byte for byte elephant-1's: OmniJev's OneJev runtime at a pinned commit with the patch applied, plus the Decision Index kit (source: \u003chttps://huggingface.co/baselabs/joey-1/raw/main/setup.sh\u003e)\n- 67 downloads and 13 likes on 30 October 2026, three days after the repository was created. No quantised build or copy by anyone else was found (source: \u003chttps://huggingface.co/api/models/baselabs/joey-1\u003e)\n\n- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md\n- All 196 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md\n\n## Compare\n\n- [elephant-1 vs joey-1](https://www.anchorterminal.com/compare/elephant-1-vs-joey-1.md): D 47.6 vs C 57.1\n- [JEV-27B-VL vs joey-1](https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1.md): C 59.5 vs C 57.1\n- [joey-1 vs mammoth-1](https://www.anchorterminal.com/compare/joey-1-vs-mammoth-1.md): C 57.1 vs D 47.7\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on baseten.co or one of its subdomains. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"joey-1\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/joey-1\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/joey-1.svg\" alt=\"joey-1 on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![joey-1 on Anchor Terminal](https://www.anchorterminal.com/badges/joey-1.svg)](https://www.anchorterminal.com/tools/joey-1)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/joey-1\"\u003ejoey-1 on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say joey-1 is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/joey-1-dark.png\n- Light: https://www.anchorterminal.com/assets/share/joey-1-light.png\n- Create a video and download its frames: https://www.anchorterminal.com/assets/listing-video/index.html?listing=joey-1\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": "2026-10-31", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "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": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Decision models", "url": "https://www.anchorterminal.com/categories/decision-models" }, { "name": "joey-1", "url": "" } ], "description": "joey-1 is Base Labs' open-weight 2B decision model, a full fine-tune of Qwen3.5-2B that takes text and images and returns a probability for every option of typed questions about a state in one prefill. Base Labs is Baseten's research lab.", "facts": [ "#16 in Decisions", "None auth", "0 desk reviews" ], "h1": "joey-1", "image": "https://www.anchorterminal.com/assets/og/tools-joey-1.png", "path": "/tools/joey-1", "published": "2026-10-01", "section": "tools", "title": "joey-1 review (2026): pricing, alternatives and grade C", "toc": null, "updated": "2026-10-30", "url": "https://www.anchorterminal.com/tools/joey-1" }, "tokens": { "markdown": 7550, "slim": 2080 }, "version": 1 }