
Anyone citing Intelligence Index numbers needs to know the graders changed, because scores across index versions are no longer directly comparable.
postMuse Spark 1.2 places Meta on the Cost per Task Pareto frontier, scoring 6 point
postQwen3.8 Max costs $1.14 per Intelligence Index task, more than double Qwen3.7 Ma
postQwen3.8 Max scores 1739 Elo on GDPval-AA, ahead of Kimi K3 (1685), effectively t
postAlibaba's Qwen3.8 Max scores 56 on the Artificial Analysis Intelligence Index atSign in to comment.
Loading comments…