Its error rate fell from 53.6% to 16.7% — and it solves twice as many coding tasks as its predecessor

On OpenAI's internal benchmark of error-inducing prompts, Terra's error rate at low reasoning effort fell from 53.6% with GPT-5.6 Terra to 16.7%, and at maximum effort to 4.3% — nearly matching the flagship GPT-6 Astra and GPT-6.1 Sol. On Terminal-Bench 4.0, a coding-agent test, Terra solved 50.3% of tasks, more than double its predecessor's 21.5%.

For the most complex coding work, OpenAI still points users to GPT-6.1 Sol and GPT-6 Astra — Terra is the cheap workhorse for the tasks that fill a workday, not the frontier.