Update README.md

README.md

@@ -28,3 +28,6 @@ Welcome to OpenGVLab! We are a research group from Shanghai AI Lab focused on Vi
 
 # Benchmarks
 - [MVBench](https://github.com/OpenGVLab/Ask-Anything/tree/main/video_chat2): a comprehensive benchmark for multimodal video understanding.
+- [CRPE](https://github.com/OpenGVLab/all-seeing/tree/main/all-seeing-v2): a benchmark covering all elements of the relation triplets (subject, predicate, object), providing a systematic platform for the evaluation of relation comprehension ability.
+- [MM-NIAH](https://github.com/uni-medical/GMAI-MMBench): a comprehensive benchmark for long multimodal documents comprehension.
+- [GMAI-MMBench](https://huggingface.co/datasets/OpenGVLab/GMAI-MMBench): a comprehensive multimodal evaluation benchmark towards general medical AI.