Bespoke Labs Releases Nimble Open Model That Hits 90% on Jev Eval

The training methodology, termed contrastive data curation, generates negative data by slightly altering facts to improve model calibration without requiring probabilities in the training set. One industry observer claimed the release violated Jev's terms of use, though the Nimble weights were produced in two days of public development. Bespoke Labs noted that since no standard benchmark exists for this model class, Nimble's performance relative to Jev may vary on other metrics.