John Yang @jyangballin · 05 May 2026
Our 200 instances range from simple (jq, ripgrep) to extremely difficult (ffmpeg, sqlite, compilers). Stats and some team favorites in the images. Improving performance on ProgramBench means that models can increasingly build software from requirements alone. https://t.co/XDDmxbayG5
12 591Views
84Likes
1Reposts
2Replies
0Quotes
10Bookmarks
Is that a lot?
4.66×vs under 10K median2 700 views is typical
178.04%Reachviews ÷ followers
0.69%Engagement rateof viewers reacted