X · @jeremyphoward
· X / Twitter
RT voratiq: After more head-to-head matches We're finding GLM 5.2 high to be … quite good Probability it beats: – Opus 4.8 xhigh: 32% – GPT-5.5 xhig…
RT voratiqAfter more head-to-head matchesWe're finding GLM 5.2 high to be ... quite goodProbability it beats:- Opus 4.8 xhigh: 32%- GPT-5.5 xhigh: 64%- Kimi K2.7 Code (next-best open): 100%Current best-estimate rank: 3rd of 56