Multimodalart released a leaderboard utilizing more than 35 benchmarks to evaluate the performance of the jev model alongside other open-weight systems. The testing process involves asking 130,000 questions to each participant to measure their effectiveness in automation, knowledge, understanding, and creativity.

The Decision Index 0.1 provides a comparative analysis for more than 30 open weights decision models. This initial release serves as a rigorous evaluation surface for assessing how different AI systems execute complex choice-based tasks relative to one another.