return2ozma@lemmy.world to Technology@lemmy.worldEnglish · 27 days agoIs Meta's Superintelligence Overhaul a Sign Its AI Goals Are Struggling?gizmodo.comexternal-linkmessage-square3linkfedilinkarrow-up127arrow-down15
arrow-up122arrow-down1external-linkIs Meta's Superintelligence Overhaul a Sign Its AI Goals Are Struggling?gizmodo.comreturn2ozma@lemmy.world to Technology@lemmy.worldEnglish · 27 days agomessage-square3linkfedilink
minus-squarenymnympseudonym@lemmy.worldlinkfedilinkEnglisharrow-up2·27 days agoThis particular coding leaderboard matches my own personal experience. Llama4 is hitting ~15% ; Claude Opus4 ~70% (I haven’t used others personally)
This particular coding leaderboard matches my own personal experience. Llama4 is hitting ~15% ; Claude Opus4 ~70% (I haven’t used others personally)