Tag
A high Pearson correlation of 0.91 is found between a model's AA Intelligence Index score and its ability to generate Base64 encoded responses, despite no explicit training for that task.
Z ai's GLM-5.2 open weights model scores 51 on the Artificial Analysis Intelligence Index, matching GPT-5.4 xhigh and sitting on the Pareto frontier of intelligence vs cost per task.
Anthropic released Claude Opus 4.5, its most intelligent model, scoring 70 on the Artificial Analysis Intelligence Index and ranking second only to Gemini 3 Pro. It achieves significant gains in coding and agentic tasks while reducing per-token pricing and maintaining strong safety performance.