update

README.md

@@ -11,7 +11,7 @@ You can find the inference code [here](https://github.com/open-compass/VLMEvalKi
 
 The [MMBench](https://mmbench.opencompass.org.cn/) benchmark contains 20 categories in the `mmbench_dev_cn_20231003.tsv` dataset. For each category, we first use CoT (Chain of Thought) consistency with the InternVL-Chat-V1-5 model to prepare the training dataset. For specific categories like nature_relation, image_emotion, image_scene, action_recognition, and image_style, we analyze the bad cases made by the InternVL-Chat-V1-5 model. We then prepare images and QA text from online sources to address these issues.
 
-After fine-tuning the 20 LoRAs, they are merged with the InternVL-Chat-V1-5 model using the TIES method. The average score on the `mmbench_test_cn_20231003.tsv` benchmark reached 82.1, placing it in the TOP 4 and outperforming GPT-4. We found this result noteworthy. This score was obtained from the uploaded inference file `submission.xlsx`. The online leaderboard average score is still being prepared. As a result, we are sharing this model publicly.
+After fine-tuning the 20 LoRAs, they are merged with the InternVL-Chat-V1-5 model using the TIES method. The average score on the mmbench_test_cn_20231003.tsv benchmark reached 82.1, which is higher than the 80.7 score of the InternVL-Chat-V1-5 model. This places it in the top 4, matching the performance of GPT-4. We found this result noteworthy. This score was obtained from the uploaded inference file `submission.xlsx`. The online leaderboard average score is still being prepared. As a result, we are sharing this model publicly.
 
 # License