model performance (IMAGE)

The University of Hong Kong

model performance

Caption

By comparing the performance with the latest versions of DeepSeek—R1 and V3—as well as GPT-4o, the HKUMed research team found that their model performed on par with these powerful online large language models.

Credit

The University of Hong Kong

Usage Restrictions

N/A

License

Original content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.