Update README.md

README.md

@@ -23,9 +23,12 @@ tags:
 
 ## News
 
-- [2026-08-03] Published the [physical robot modification guide](https://github.com/dexmal/opendm/blob/main/docs/en/robot_platforms.md) for AgileX COBOT Magic and DOS-W1, documenting camera changes and the robot-name mapping used by the algorithm.
-- [2026-07-24] DM0.5 has added the SO101 pick cube fine-tuned checkpoint and the LoRA SFT workflow. See the [DM05 SO101 LoRA Training Guide](https://github.com/dexmal/opendm/blob/main/docs/en/dm05_so101_lora_training.md).
-- [2026-07-17] DM0.5 has open-sourced the RoboTwin2.0 generalist model checkpoint, along with the supervised fine-tuning (SFT) code built upon the DM0.5 pretrained model. See the [DM05 RoboTwin2.0 Training and Evaluation Guide](https://github.com/dexmal/opendm/blob/main/docs/en/dm05_robotwin2.md).
+- [2026-09-14] 🏆 **DM0.5 ranked first** in Instruction Following, Spatial Reasoning, Robustness, and General Manipulation on [RoboColiseum](https://robocoliseum.ai/leaderboard), making it the only model to sweep all four leaderboards.
+- [2026-08-26] Released [DM05-MEM-Robodojo-Sim](https://huggingface.co/Dexmal/DM05-MEM-Robodojo-Sim), a fine-tuned model for ARX X5 bimanual manipulation tasks in RoboDojo-Sim. See [XPolicyLab PR #101](https://github.com/XPolicyLab/XPolicyLab/pull/101) for evaluation integration.
+- [2026-08-25] 🏆 **DM0.5 topped** the [RoboDojo-Sim](https://robodojo-benchmark.com/) leaderboard, achieving an overall score of 24.90 and an average success rate of 19.34%, with a particularly pronounced lead in the Memory track.
+- [2026-08-03] Published the [physical robot modification guide](docs/en/robot_platforms.md) for AgileX COBOT Magic and DOS-W1, documenting camera changes and the robot-name mapping used by the algorithm.
+- [2026-07-24] DM0.5 has added the SO101 pick cube fine-tuned checkpoint and the LoRA SFT workflow. See the [DM05 SO101 LoRA Training Guide](docs/en/dm05_so101_lora_training.md).
+- [2026-07-17] DM0.5 has open-sourced the RoboTwin2.0 generalist model checkpoint, along with the supervised fine-tuning (SFT) code built upon the DM0.5 pretrained model. See the [DM05 RoboTwin2.0 Training and Evaluation Guide](docs/en/dm05_robotwin2.md).
 - [2026-07-09] DM0.5 is officially released. Read the [technical blog](https://www.dexmal.com/blog/dm0.5/index_en.html) for more details.
 
 ## Introduction