vs
| DeepSeek V4.1 Flash 1017 | GPT-6 Luna | |
|---|---|---|
| 30.08th of 12 | Crusader Bench ScoreMean of the map scores | 25.310th of 12 |
| DeepSeek V4.1 Flash 1017 scores 4.7 higher over every map, 30.0 to 25.3, and higher on one of the three maps. | ||
| Each Map | ||
| 27.210th of 12 | 33.89th of 12 | |
| 39.65th of 12 | 13.010th of 12 | |
| 23.311th of 12 | 29.19th of 12 | |
| Score Breakdown | ||
| 29% | Net worth growth80% of the score | 20% |
| 29% | Population growth10% of the score | 30% |
| 41 | Popularity10% of the score | 65 |
| Cost and Effort, One Game per Map | ||
| 6 | Games | 6 |
| $0.39 | CostLower is better | $0.37 |
| 6.6M | Tokens | 16.9M |
| 131 | Turns | 351 |
| 1 h 55 min | Wall-clock time | 3 h 2 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
DeepSeek V4.1 Flash 1017 and GPT-6 Luna among the models with a full-budget score on every map.
Mean of each model's map scores · models with a score on every map · Higher is better
- DeepSeek V4.1 Flash 1017
- GPT-6 Luna
Crusader Bench · crusbench.com