Simon Willison(@simonw)
I tried a 15MB, 30 page text-heavy PDF and Opus 4.7 reported 60,934 tokens while 4.6 reported 56,482...
5.0Score
AI 深度提炼
- Opus 4.7相比4.6对PDF的token计数仅增加8%，增幅温和。
- 结构化文档（如PDF）的token膨胀率显著低于原始文本。
- 版本升级对不同输入格式的影响差异值得关注。
#Opus#Token计数#AI模型
打开原文Simon Willison on X: "I tried a 15MB, 30 page text-heavy PDF and Opus 4.7 reported 60,934 tokens while 4.6 reported 56,482 - that's a 1.08x multiplier, significantly lower than the multiplier I got for raw text." / X
Don’t miss what’s happening
People on X are the first to know.
Post
See new posts
Conversation
I tried a 15MB, 30 page text-heavy PDF and Opus 4.7 reported 60,934 tokens while 4.6 reported 56,482 - that's a 1.08x multiplier, significantly lower than the multiplier I got for raw text.
·
3
14
New to X?
Sign up now to get your own personalized timeline!
Sign up with Apple
By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.
Relevant people
-  Simon Willison @simonw Follow Click to Follow simonw Creator @datasetteproj , co-creator Django. PSF board. Hangs out with @natbat . He/Him. Mastodon: https://fedi.simonwillison.net/@simon Bsky: http://simonwillison.net
Trending now
What’s happening
Trending in United States
Happy Lesbian Visibility Week
Trending in United States
Alleges
Sports · Trending
Justin Jefferson
Sports · Trending
John Lynch
|
|
|
|
|
More
© 2026 X Corp.