Skip to content
Better HN
Top
New
Best
Ask
Show
Jobs
Search
⌘K
0 points
alach11
1mo ago
0 comments
Save
Share
I ran an internal (oil and gas focused) benchmark yesterday and found Opus 4.7 was 50% cheaper than Opus 4.6, driven by significantly fewer output tokens for reasoning. It also scored 80% (vs. 60%).
0 comments
1 comments · 1 top-level
default
top
newest
oldest
stingraycharles
1mo ago
That’s just adaptive reasoning, not related to the increased tokenizer costs.
1 more reply
j
/
k
navigate · click thread line to collapse