DeepSeek V4.1 Flash 1017 vs GPT-6.1 Sol

Each Map
DeepSeek V4.1 Flash 1017DeepSeek · reasoning medium	vs	GPT-6.1 SolOpenAI · reasoning medium
30.08th of 12	Crusader Bench ScoreMean of the map scores	69.71st of 12
GPT-6.1 Sol scores 39.7 higher over every map, 69.7 to 30.0, and on every map.
27.210th of 12		72.32nd of 12
39.65th of 12		87.01st of 12
23.311th of 12		49.82nd of 12
Score Breakdown
29%	Net worth growth80% of the score	71%
29%	Population growth10% of the score	48%
41	Popularity10% of the score	78
Cost and Effort, One Game per Map
6	Games	6
$0.39	CostLower is better	$2.36
6.6M	Tokens	13.4M
131	Turns	286
1 h 55 min	Wall-clock time	2 h 11 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.