Tinker @tinkerapi · 28 Aug 2026
GLM-5.3 from @Zai_org is now available on Tinker with 256k context. With scaled up post-training from the same base as GLM-5.2, it is currently the strongest open-weights model on coding evals such as Terminal-Bench 3.0 and DeepSWE 1.1.
8 097Views
152Likes
6Reposts
8Replies
1Quotes
24Bookmarks
Is that a lot?
0.62×vs this author's median13 023 views is typical
29Percentile for this authorof 7 recent posts
2.94×vs 10K–100K median2 751 views is typical
57.06%Reachviews ÷ followers
2.06%Engagement rateof viewers reacted