Update model card

README.md

@@ -69,7 +69,7 @@ MOMO is pre-trained on ~12 million samples (~4M per sensor) from Mars orbital im
 
 ## Evaluation
 
-MOMO is evaluated on 9 downstream tasks from [Mars-Bench](https://arxiv.org/abs/2510.24010) (4 classification, 5 segmentation), outperforming ImageNet pre-training, earth observation foundation models (SatMAE, CROMA, Prithvi, TerraFM), sensor-specific pre-training, and fully-supervised baselines.
+MOMO is evaluated on 9 downstream tasks from [Mars-Bench](https://mars-bench.github.io/) (4 classification, 5 segmentation), outperforming ImageNet pre-training, earth observation foundation models (SatMAE, CROMA, Prithvi, TerraFM), sensor-specific pre-training, and fully-supervised baselines.
 
 ---