cm0002 to AI - Artificial intelligence@programming.devEnglish · 1 month agoDeepSeek's Terminal-Bench score quietly jumped 25.8 points with V4-Flash upgrade (56.9 in April)imagemessage-square1linkfedilinkarrow-up114arrow-down14
arrow-up110arrow-down1imageDeepSeek's Terminal-Bench score quietly jumped 25.8 points with V4-Flash upgrade (56.9 in April)cm0002 to AI - Artificial intelligence@programming.devEnglish · 1 month agomessage-square1linkfedilink
minus-squareAuth@lemmy.worldlinkfedilinkEnglisharrow-up3·1 month agoNo it didnt. There was a big announcement post about this last week. Its all anyone is talking about.