Meta's Muse Spark 1.1 outperforms GLM-5.2 in coding with lower costs
Meta's Muse Spark 1.1 scores 51 on the Artificial Analysis Intelligence Index, up 8 points in three months.
Published 2j1 source
Lire en français
≈ 22s
38 %
The model's hallucination rate dropped from 73% to 38%
The fact
It outperforms GLM-5.2 in coding with a score of 71.3 at a lower cost ($0.26 per task).
The model's hallucination rate dropped from 73% to 38%.