Adam Kucharski (@adamkucharski): "GPT-5.6 Sol cheated so much that METR couldn't reliably evaluate it: https://metr.org/blog/2026-06-26-gpt-5-6-sol/"

Make money doing the work you believe in

Adam Kucharski

5d

Understanding the unseen

GPT-5.6 Sol cheated so much that METR couldn't reliably evaluate it: metr.org/blog/2026-06-2…

Jun 26

at

8:57 PM

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts

Make money doing the work you believe in

Log in or sign up