Article
CommunityJev Models & Reimplementations
Towards Foundation Decision Models: Drex
arXiv paper introducing Drex, a family of four open decision models at 8B, 9B, 35B with 3B active, and 27B parameters. Reports 67.52 on Decision Index 0.4.1 versus 60.70 for Jev 1.14.0.
- Format
- Article
- Reading time
- 2 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- Four open decision models: 8B (DLM), 9B (v1.5), 35B with 3B active (v2.0), and 27B (Max).
- Requests pair a state (document, record, or agent context, optionally with images) with questions offering options, yes/no, or ordered scales.
- Training combines supervised fine-tuning with reinforcement learning from adjusted feedback (RLAF), plus vision tuning for Max.
- Max scores 67.52 on the Decision Index 0.4.1 public suite versus 60.70 for Jev 1.14.0.
- Max answers a typical request in 183 ms, against about 2.0 s for GPT-6 Sol and 3.5 s for Claude Opus 5.5.
Questions about this entry
Short answers drawn from the linked project or page.
Four open decision models: DLM at 8B parameters, v1.5 at 9B, v2.0 at 35B with 3B active, and Max at 27B parameters.
Each request pairs a state, such as a document, record, or agent context optionally with images, with questions about it. Each question asks for a choice among options, a yes/no judgment, or a score on an ordered scale.
Training combines supervised fine-tuning with reinforcement learning from adjusted feedback (RLAF), plus vision tuning for Max. Ablations show RLAF improves accuracy and consistency losses improve robustness to option order.
On Decision Index 0.4.1, Max scores 67.52 on the public suite against 60.70 for Jev 1.14.0, which the paper describes as a new state of the art among the decision models compared.
Max answers a typical request in 183 ms, against about 2.0 s for GPT-6 Sol and 3.5 s for Claude Opus 5.5.
Yes. All four models are open source, and the paper points to the nace-ai/drex-decision-models repository.
Consistency losses during training improve robustness to option order, and the paper reports that Max's outputs are stable under option reordering.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Standard One SH (StandardThinking)
LinkedIn: What multimodal decision models actually change, and what they do not.
LinkedInJevDirectory.org
Hacker News: Decision Index 0.2.1 scores open reproductions of Jev on a frozen suite.
jackbravo4 pointsDecision Index 0.2.1 – 70 open reproductions of TypeSafe Jev's Decision ModelRead the thread on Hacker NewsHacker News: Pointer to a DiffusionGemma plus vLLM tutorial for a Jev-shaped classifier.
1 pointHow to build a Jev-style classifier with DiffusionGemma and vLLMRead the thread on Hacker NewsMore Jev resources like this
Zuse is a family of three decision models (4B, 9B, 27B) that train a low-rank adapter and pointer head on frozen open-weight bases for 27 European languages. The 27B model reaches 87.5% accuracy with pooled expected calibration error of 0.016 on an 11-source European suite.
Jev Models & ReimplementationsArticle#arxiv#open-models#calibration
Community
Open-weight vision-language judge that takes a task instruction plus 10 frames of a robot manipulation attempt and predicts success or failure with calibrated probabilities in a single forward pass. Released with inference code and a 20,628-prediction evaluation set.
Jev Models & ReimplementationsArticle#arxiv#open-models#evaluation
Community
A family of 0.8B-9B ophthalmic decision models that score candidate answers without autoregressive decoding, trained on RetiJev-Data: 78,158 clinical-decision and diagnosis questions and 50,074 guideline-grading questions. RetiJev-9B answers a case in 158 ms on one GPU.
Jev Models & ReimplementationsArticle#arxiv#open-models#benchmark
Community
Open-weight eligibility scorer that LoRA-adapts Qwen models with a pointer head to score natural-language answer options in one forward pass, trained on TREC Clinical Trials 2021 and evaluated on 6,975 pairs from 50 unseen synthetic patients.
Jev Models & ReimplementationsArticle#arxiv#open-models#evaluation
Community
arXiv paper proposing TimesJev, a time series System 1 model in Jev's instant-decision shape. It formalizes System 1 sufficiency and learns a compressed representation preserving key frequency patterns, reporting over 62% better results and 62.9% less inference time than fine-tuned reasoning models.
Jev Models & ReimplementationsArticle#arxiv#research#benchmark
Community
arXiv paper introducing ReListen, a training-free method in which a frozen audio language model runs a Jev-style scan: it scores each 20-second window by the probability it helps answer a question, then answers from the highest-scoring minute of hour-long recordings.
Jev Models & ReimplementationsArticle#arxiv#research#benchmark
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.