Gemini 4 Argon ranks first on CrusaderBench, ahead of Claude Opus 5.5
Overview
Hesam Hesamation says Gemini 4 Argon ranked first on his CrusaderBench, beating Claude Opus 5.5 by an unspecified margin.
CrusaderBench tests how well AI models grow an economy in the strategy game Stronghold Crusader. Paige Bailey of Google shared the result on X on October 14, 2026, praising Argon's ability to manage and scale colonies in games.
Hesamation says Argon used tactics usually seen only from professional players, such as building wells to increase the working population. The score and the full benchmark results have not been published in the reports.
Written by AI from the articles below · updated Oct 14, 9:59 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
👩💻 Paige Bailey@DynamicWebPaigeXGemini 4 Argon tops CrusaderBench, beating Claude Opus 5.5 on strategic economy buildingAIPaige Bailey of Google highlights Gemini 4 Argon's ability to dynamically manage and scale colonies in games. Separately, Hesam Hesamation reports that Argon ranked first on his CrusaderBench, which tests models' strategic economy building in Stronghold Crusader, beating Opus 5.5 by a margin. Argon reportedly used tricks usually seen only from pro players, such as building wells to increase the working population.
Heat trend
Not enough continuous observations to show a trend yet.