Expired75% confidenceFactTime unknown
In the DEF CON Goldbug cryptography challenge test, GPT-5.1 Pro correctly identified the ADFGX cipher using approximately 30 minutes of thinking time, while no Claude model was able to do so.
1
Sources
75%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
GPT-5.1 Pro Deep Dive: The Smartest AI Trapped in the Worst Interface
bilibili安得广厦千万间678
Related Entities
Related Claims
UnverifiedAfter approximately 40 minutes of total compute time, GPT-5.1 Pro ultimately correctly solved the Smuggler's Manifest cipher puzzle, with the answer being 'WALLET PICKER'.74% similarUnverifiedGPT-5.5 Pro produced a logically consistent proof of Erdős problem No. 710 within 22 minutes, but was in fact restating an old conclusion that had already been proven decades ago.66% similarUnverifiedGPT-5.5 slightly underperformed Claude's yet-to-be-released new model on the OS World Verified benchmark.63% similarUnverifiedGPT-4 is capable of solving medium-difficulty binary exploitation challenges in CTF competitions, whereas GPT-3 is almost unable to complete full exploit development.62% similarUnverifiedGPT-5.2 Pro's thinking time in deep reasoning tests reached as long as 14 minutes.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/12474API
curl https://kongchang.com/api/v1/knowledge/claims/12474MCP
get_claim(id=12474)