Claude @claudeai · 01 Sep 2026
Across our benchmarks, the model sets a new standard. It scores 52.6% on Terminal-Bench-Science 0.1, more than double Fable 5. On Terminal-Bench 4.0, it scores 55.8% against 42.0% for Fable 5. https://t.co/aSb72LSxee
1 110 907Views
5 460Likes
447Reposts
126Replies
392Quotes
626Bookmarks
Is that a lot?
2.34×vs this author's median475 276 views is typical
80Percentile for this authorof 20 recent posts
16.7×vs 1M–10M median66 438 views is typical
63.04%Reachviews ÷ followers
0.58%Engagement rateof viewers reacted