Decision Index 0.2 Adds 29 Models and 21 Benchmarks; AutoJev-27B Takes Open-Weights Lead

multimodalart · x · 2026-09-24

multimodalart released Decision Index 0.2, upgrading from 0.1 with a better formula, +29 jev-like models and +21 benchmarks, aiming to surface the best model at every size, speed and use-case.

The 0.1 launch compared jev against 30+ open-weight decision models across 35+ benchmarks, asking each model 130K questions spanning knowledge, automation, understanding and creativity. In 0.2, AutoJev-27B by Perplexity CTO Denis Yarats took the open-weights lead, trailing jev by just 0.8 points.

Related event: Decision Index 0.2 released; Perplexity CTO's model tops open ranking(2 posts)→

Original post →

More from Models

Models channel →