elie @eliebakouch · 02 Sep 2026
long context benchmark (MRCR) going crazy, very interesting would be great to have other benchmarks such as graphwalks for long context and release test time scaling curves and not just raw benchmark scores in general https://t.co/yfLD2RDlk3
6 722Views
75Likes
0Reposts
7Replies
0Quotes
8Bookmarks
Is that a lot?
0.21×vs this author's median31 519 views is typical
14Percentile for this authorof 7 recent posts
2.32×vs 10K–100K median2 896 views is typical
27.88%Reachviews ÷ followers
1.22%Engagement rateof viewers reacted