tweetindex

LlamaIndex 🦙 @llama_index · 02 Sep 2026

ExtractBench is now live on @Kaggle. It tests schema-guided document extraction on the documents most likely to break downstream agents and workflows, including long record lists, noisy scans, handwriting, and complex tables. The benchmark covers 370 enterprise documents across https://t.co/rTDYMUABll
9 054Views
31Likes
6Reposts
3Replies
1Quotes
11Bookmarks

Is that a lot?

1.71×vs this author's median5 303 views is typical
50Percentile for this authorof 8 recent posts
1.53×vs 100K–1M median5 930 views is typical
7.57%Reachviews ÷ followers
0.45%Engagement rateof viewers reacted

Compare with the benchmark table →

Open on X →