The benchmark picture, largely via the evaluation firm Artificial Analysis, backs up the pricing story. Terra gains 6 points on the Intelligence Index over GPT-5.6 Terra at maximum reasoning effort while costing less than a third per task, $0.40 versus $1.40, and gains of 7 to 13 points at lower effort levels. Artificial Analysis calls it a new benchmark for intelligence per dollar, placing it on the Pareto frontier, the point where cost and performance can no longer both improve at once.

Coding is where the jump is sharpest. On Terminal-Bench 4.0, Terra solves 50.3 percent of tasks at maximum reasoning effort, up from 21.5 percent for its predecessor, a 20-point improvement that Artificial Analysis says puts it in the same tier as the larger GPT-6.1 Sol. On the Agents' Last Exam benchmark, OpenAI says Terra matches GPT-6 Astra at one-tenth the token price and runs more than three times faster than both Astra and Sol. For the most demanding coding tasks, though, OpenAI still recommends GPT-6.1 Sol and GPT-6 Astra.

The model also guesses far less when it does not know an answer: on Artificial Analysis's private AA-Omniscience benchmark it resorts to guessing 38 percent of the time, down from 88 percent for GPT-5.6 Terra, with accuracy up two points. On security, Terra meets OpenAI's "Critical" threshold under its Preparedness Framework and inherits GPT-6 Astra's safeguards. Its system card reports a 98.8 percent defence rate against indirect prompt injection attacks, where malicious instructions are buried in third-party content, up from 96.2 percent for the predecessor.

GPT-6.1 Terra is available now through the API and in ChatGPT Work and Codex for Plus, Pro, Enterprise and Edu users. OpenAI positions it for everyday work tasks, from drafting proposals to interpreting technical drawings to filling out forms, combining fast visual reasoning with precise computer control.