AI Briefing#decision-model
The latest AI and developer news about #decision-model, with the original source and a short summary.
The latest AI and developer news about #decision-model, with the original source and a short summary.
The early release of the small model on Gemma 4 E4B scores 0.811 on the Werdykt benchmark and requires basal engine 2.8.0.
Kakao's Kanana-2-v-decide-3b-2611 is a decision model that accepts text, JSON, or chat history with optional images to output probabilities for choice, yes/no, or scale-based answers.
Kakao has released the 3B-scale multimodal decision-making model Kanana-2-v-decide as open source.
Baseten unveiled joey-1, a 2B decision model, offering a price of $0.01 per 1M API input tokens.
The model uses a 255-way readout head to output probabilities over candidate answers in a single forward pass, avoiding token generation entirely.
Apache 2.0 licensed tool processes 491 questions per second on an RTX 4090 by reading content once for multiple decision queries.
An open-source decision model trained on 2,676 contrastive data points that flip the correct answer by changing just one fact
The new version adds image input support and an experimental long-context mode for processing documents and logs.
Presents a method for training and serving LLMs like Qwen3.5 by attaching decision heads to perform classification and judgment tasks
Offers a lightweight decision model specialized for classification and routing tasks at $0.042 per 1M input tokens
Qwen3.5-4B achieves 81.4% on JevBench without training, while fine-tuning proves effective for small models
The model scores 44.86 on Decision Index 0.2.1, ranking #1 among 4B models, and processes 1M-token documents in ~3 seconds via API.
No open model has surpassed Jev, but Cygnet recorded the top score on JevBench.
The 26B parameter model achieves an 85.71% overall accuracy across 11 benchmarks, outperforming its base model Qwen3.8-27B and the Jev baseline.
A Jev-compatible API-based model offering low latency and calibrated probabilities with 0 output tokens
A Jev-compatible open-weight model that returns probability distributions in a single forward pass to address LLM hallucination and latency issues.
Released six open-weight models and a Studio for testing that return the probability of the optimal choice among candidates instead of generating text.
Jared Palmer released Kev, a lightweight decision-making model based on Qwen3.5, offering simultaneous processing of Yes/No, multiple-choice, and rating tasks with Apple Silicon support.
The open-source Kev series of decision models based on Qwen3.5 has been released, offering TypeSafe API compatibility and detailed performance metrics.
A researcher released 'Laya', a fully open-source decision model responding to the closed model 'Jev', achieving 6-8x faster speed and hallucination blocking compared to Jev.