UT Austin System Beats Human Champion at Times Crossword Championship
A University of Texas at Austin team's automated system, Darmok, solved all seven British cryptic crossword puzzles error-free at the 2026 Times Crossword Championship, beating the human champion by 3 minutes 13 seconds in the Final, the first automated system to reach superhuman performance in this event. Notably, the primary model provider slowed sharply during the Final, and backup routing supplied 17 of the 30 answers, underscoring the value of multi-model redundancy for latency-critical tasks.
Full Report
Rohan Paul (@rohanpaul_ai) · 2026-11-21 22
"the first automated system to reach superhuman performance on British cryptic crosswords."
From UT Austin paper
British cryptic crosswords hide each answer behind misleading wordplay, and tournament rules rank any grid with 1 error behind every perfect one. Cloud AI models can now solve them, but API calls still stall or time out.
At the 2026 Times Crossword Championship, their system "Darmok" solved all 7 puzzles error-free and won the Final by 3m 13s over the human champion. During that Final the main provider slowed sharply, and backup paths supplied 17 of the 30 answers.
