Codex User Compares OpenAI Terra 6.1 and Anthropic Opus 5.5: Critiques Model Efficiency and Cost-Effectiveness

Original title: 185 Days of Codex: Worse Limits, Cheaper Models, Less Work Done. How Is This Progress?

One user, following 185 days of experience with Codex, reports that OpenAI Terra 6.1's performance and cost-efficiency are no longer competitive with Anthropic Opus 5.5. The user points out that Terra 6.1 often fails on complex tasks, costing roughly 90% more than Sol 6.1 Medium to achieve comparable results. The author also expresses concerns about OpenAI's equitable feature rollout and the perceived diminishing value of the model family.

The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.