Steve Hou @stevehou · 03 Sep 2026
We evaluated GPT 6 Astra at @databricks and it claims the new SOTA on our OfficeQA Pro & Pro V2 benchmarks, using our Genie harness. It also improves significantly from gpt 5.6 sol on the $ per task. Throughout our benchmarks, it shows a clear step up on data reasoning and https://t.co/mPOQjQ9cF8
49 668Views
406Likes
37Reposts
16Replies
8Quotes
0Bookmarks
Is that a lot?
6.70×vs this author's median7 414 views is typical
83Percentile for this authorof 6 recent posts
20.8×vs 10K–100K median2 392 views is typical
84.47%Reachviews ÷ followers
0.94%Engagement rateof viewers reacted