AWS Launches a Local Answer to TypeSafe's Jev Decision Model
The model uses a Qwen3.5-2B base and scores developer-supplied options, with AWS saying it returns decisions in under 100 milliseconds on an Nvidia RTX 3090.
10 Articles
10 Articles
Amazon releases its own Jev clone as decision models flood the web
Amazon Web Services' Strand Labs has released the latest Jevalike decision model, Strands Decider 2B.
Amazon unveils a free, fast, open source Jev killer: Strands Decider 2B makes decisions in fractions of a second
Amazon has produced a genuinely competitive Jev alternative whose strongest differentiation is not superior benchmark performance, but that it is open, self-hostable and reproducible.
AWS Strands Labs Releases Strands Decider 2B: An Open Source Decision Model That Picks Options in About 115 ms
AWS's Strands Agents team released Strands Decider 2B, an Apache-2.0 decision model built on Qwen3.5-2B-Base. It returns choices, yes/no probabilities and scores with calibrated confidence in one forward pass, never text. It runs at a 115 ms median on an RTX 3090 and scores 0.723 on the JevBench public set, which makes it a fast local option for routing, tool selection and guardrails in AI agents.
Amazon launched Strands Decide 2B, an open and small model that selects options for AI workflows and offers a measure of confidence.
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium













