Techub News reports that, according to Decrypt, the U.S. NIST-affiliated organization CAISI released an evaluation report stating that DeepSeek V4 Pro is approximately 8 months behind leading U.S. AI models. The organization used the IRT scoring system to evaluate based on nine benchmark tests, two of which are non-public datasets. The evaluation has sparked skepticism among experts. The Stanford 2026 AI Index shows that the performance gap between China and the U.S. AI has narrowed to 2.7%, and DeepSeek performs close to top U.S. models in public benchmark tests. Additionally, the cost comparison excluded most U.S. models, only comparing with GPT-5.4 mini.

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin