Live site · found by @Jevalscom
Jev vs LLM benchmark for decision models
Independent benchmark comparing Jev and six LLMs on 31,500 human-labelled decisions, covering accuracy, calibration, price, and speed
Jev judged this in 471 ms for $0.00008
Found something worth sharing?
Drop the link and Jev reads it on the spot. What belongs lands in the community feed with your name on it.
More from the community
GitHubTools and apps
Semantic code search for what code does
Find code by its behavior using natural language queries without indexes or embeddings
Jev · 318ms
@MINTr5dwGitHubTools and apps
Terminal AI Research Assistant That Verifies Claims
Ask questions in your terminal; get web and onchain answers with each claim verified before you see it. No login needed
Jev · 413ms
@jevbook
Live siteAgents and browsers
Separating Agent decisions from LLM generation in system design
A guide to separating agent decision-making from LLM generation, using fast decision layers for routing, scoring, and gating in a testable architecture
Jev · 393ms
@agentbuff_dev