@kalomaze yeah
kalomaze@kalomaze
@scaling01 i feel they could have picked better colors
10:32 AM · Jun 26, 2026 · 449 Views
ExploitBench data shows GPT-5.6 Sol reaches 75% capability, outpacing older GPT-5.5 and GPT-5.4 variants on token efficiency
Sol remains below the 80% Mythos 5 reference line.
373162.8K
Sentiment
Sentiment building, check back later.
Cluster Engagement
Digg Deeper
No Digg Deeper questions have been answered for this story yet.
Posts from X
Most Activity
Most Activity
VIEWS2
Jennie Wuu@n1721203925204
@TheRealAdamG what's the official logo for 5.6 Sol anyway 😂
3hViews 2