Artificial Analysis just added GLM 5.2 to their open vs closed frontier timeline, here's a flipped version which gives the lag time of OSS perf on their intelligence index
3:03 PM · Jun 17, 2026 · 5K Views
Together AI's Yaroslav Bulatov finds the performance lag between open-weights and proprietary frontier models has shrunk to under three months
DeepSeek V4 Pro narrows the lag to 2.2 months.
560299.1K
Sentiment
Sentiment building, check back later.
Cluster Engagement
Digg Deeper
No Digg Deeper questions have been answered for this story yet.
Related links
Posts from X
Most Activity
Most Activity
VIEWS2.9KBOOKMARKS2LIKES28REPLIES1
Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)@teortaxesTex
Very nice chart, except it ignores non-released models like early Mythos
Yaroslav Bulatov@yaroslavvb
Artificial Analysis just added GLM 5.2 to their open vs closed frontier timeline, here's a flipped version which gives the lag time of OSS perf on their intelligence index
5hViews 2.9KLikes 28Bookmarks 2
Yaroslav Bulatov@yaroslavvb
for future reusability https://yaroslavvb.github.io/artificial-analysis-oss-lag/
Yaroslav Bulatov@yaroslavvb
Artificial Analysis just added GLM 5.2 to their open vs closed frontier timeline, here's a flipped version which gives the lag time of OSS perf on their intelligence index
6hViews 1.1KLikes 4Bookmarks 1
dani@absenteewarlord
@teortaxesTex is there any reason to think chinese labs don't also have non-released models?
5hViews 57Likes 2