Kimi K3.1 Pro vs Muse Wonder

Each Map
Kimi K3.1 ProMoonshot AI · reasoning high	vs	Muse WonderMeta · reasoning medium
32.15th of 12	Crusader Bench ScoreMean of the map scores	31.17th of 12
Kimi K3.1 Pro scores 1.0 higher over every map, 32.1 to 31.1, and higher on two of the three maps.
40.94th of 12		38.06th of 12
17.88th of 12		23.97th of 12
37.64th of 12		31.68th of 12
Score Breakdown
27%	Net worth growth80% of the score	28%
40%	Population growth10% of the score	32%
63	Popularity10% of the score	59
Cost and Effort, One Game per Map
6	Games	6
~$3.40	CostLower is better	$5.07
8.7M	Tokens	8.5M
168	Turns	169
2 h 20 min	Wall-clock time	1 h 57 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.