Models · The Decoder ·
Meta's Muse Spark 1.1 outperforms GLM-5.2 in coding and costs slightly less
Meta’s Muse Spark 1.1 reached a score of 51 on the Artificial Analysis Intelligence Index, up eight points in three months. It slightly outperformed GLM-5.2 in coding with a 71.3 score while costing $0.26 per task, and its hallucination rate fell from 73% to 38%.