CryptoWorld News: V4-Pro scored 3,206 points on Codeforces, surpassing GPT-5.4's 3,168 points and Gemini 3.1 Pro's 3,052 points, setting a new benchmark record. Technical reports show that V4-Pro performs excellently in coding, but still lags behind Opus and Gemini in long context and knowledge-intensive evaluations. Specifically, V4-Pro scored 62.0 on the CorpusQA 1 million benchmark, trailing Opus 4.6's 71.7 by 4.6 points; on MRCR 1 million, it scored 83.5, with Opus 4.6 leading by nearly 10 percentage points at 92.9. It should be noted that the above comparisons do not include the recently released GPT-5.5 and Opus 4.7, and the gap between V4 and the latest closed-source models requires further verification.

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