Eighty-two percent. That's the number OpenAI put front and center when it announced that GPT-5.6 works inside Kiro.
Not speed. Not accuracy. Cost.
Fact
The facts: the whole GPT-5.6 family, that is the Sol, Terra and Luna variants, is available in Kiro, AWS's spec-driven development agent that turns intent into requirements, a technical design and executable tasks. OpenAI and AWS worked together on tuning the environment. By OpenAI's own figures, on Terminal-Bench 2.1 the GPT-5.6 Terra variant completes successful tasks in Kiro at around 82 percent lower cost. Verifying execution through property-based tests is among the listed capabilities. Source: OpenAI's announcement from 24 August 2026.
Whose number is it
Theirs. Measured by OpenAI, in an environment tuned by OpenAI and AWS, on a task they chose. There's no independent verification. So I read it as an advert with a precise number attached, not an engineering fact.
The logic underneath, though, holds up. The spec feeds the model clear requirements and context from the start. Less wandering, fewer wasted attempts, fewer tokens burned in the wrong direction.
They aren't selling a smarter model. They're selling less waste.
For a team paying the bill at the end of the month, that's more interesting than any quality benchmark. And it's easy to check for yourself: look at your own invoice a month from now, not their chart.
Official primary sources
OpenAI: GPT-5.6 in KiroThe visual is generated code-art, no third-party images.