Did Codex Reset
GitHub

Artificial Analysis: Intelligence Index high rose from 17 to 58 in a year

Artificial Analysis says its Intelligence Index versus cost-per-task Pareto frontier has changed significantly over the past 18 months.

One year ago, the highest-scoring model was GPT-5 mini (high), at 17 on v4.3 of the Intelligence Index and about $0.05 per task. As of last week, Claude Opus 5.5 set the highest score to date at 58 and about $5.98 per task.