LongCat-2.5 on Humanity’s Last Exam
Changed by Meituan on
Removed the old version
Meituan changed the footnote on LongCat-2.5’s 63.1 on Humanity’s Last Exam with tools. Its model card said the score was on the text-only subset until Nov 9. From Nov 10 it says the full set, and the launch post now says the same. The score stayed at 63.1, and neither page notes the edit.

Before and after


- LongCat-2.5 model card, Nov 9 revisionhuggingface.co
- LongCat-2.5 model card, Nov 10 revisionhuggingface.co
- Introducing LongCat-2.5longcat.ai