vs

Claude Haiku 5.5Anthropic · reasoning mediumKimi K3.1 ProMoonshot AI · reasoning high
22.411th of 12Crusader Bench ScoreMean of the map scores32.15th of 12
Kimi K3.1 Pro scores 9.7 higher over every map, 32.1 to 22.4, and on every map.
Each Map
25.011th of 1240.94th of 12
17.29th of 1217.88th of 12
25.110th of 1237.64th of 12
Score Breakdown
16%Net worth growth80% of the score27%
19%Population growth10% of the score40%
76Popularity10% of the score63
Cost and Effort, One Game per Map
6Games6
~$0.15CostLower is better~$3.40
7.6MTokens8.7M
138Turns168
1 h 20 minWall-clock time2 h 20 min

Ranks are among the models with a full-budget score; over every map, among those with one on every map. Net worth and population growth are each the share of a person’s gain over doing nothing. Cost and effort add up one game on each map, the mean of its games where a model played a map more than once.

Where They Stand

Claude Haiku 5.5 and Kimi K3.1 Pro among the models with a full-budget score on every map.

Crusader Bench · crusbench.com

The Games