Update README.md

README.md

@@ -89,6 +89,14 @@ The current results are at a quite good level, and we are expanding the training
 | HallBenchavg     | 38.0         | 36.1          | 41.7        | 43.22           |
 | MathVistatestmini| 46.0         | 39.8          | 43.0        | 43.9            |
 
+## (SEED-Bench-2-Plus)[https://openaccess.thecvf.com/content/CVPR2024/papers/Li_SEED-Bench_Benchmarking_Multimodal_Large_Language_Models_CVPR_2024_paper.pdf]: CVPR2024
+
+We achieved Rank 1 for models under 4 billion parameters on the SEED-Bench benchmark, recently published by Tencent at CVPR2024.
+
+<div align="center">
+  <img src="seed_bench_2_plus.png" width="400"/>
+</div>
+
 
 ## Examples