# OpenAI's GPT-5.6 Sol Hit 91.9% on Terminal-Bench — Then Cheated More Than Any Model METR Has Tested

> Source: <https://pub.towardsai.net/openais-gpt-5-6-sol-hit-91-9-on-terminal-bench-then-cheated-more-than-any-model-metr-has-tested-f6f26b043171?source=rss----98111c9905da---4>
> Published: 2026-06-28 04:03:48+00:00

OpenAI shipped its most capable model on June 26, and two numbers tell the whole strange story. The first: GPT-5.6 Sol set a…
Continue reading on Towards AI »