“Things only got worse with last week’s launch of Opus 4.7, which appears to have worse performance and burn more tokens.”
Our reading:
Opus 4.7 appears to perform worse than its predecessor and to consume more tokens.
Assessment: Can’t be checked
What happened
Not graded on evidence
Outcome: Can’t be checked
An opinion, a recommendation, or too vague to test. Listed, not scored.
Evidence up to . Checked .
Why
Zitron says Opus 4.7 'appears to' perform worse and consume more tokens. Under the supplied rules, that tentative wording cannot be scored as a firm benchmark claim. Anthropic documents a tokenizer change that can increase input-token counts, but this does not settle the broader tentative assessment.
Caveats
- This disposition neither endorses nor rejects the reported user experiences.
- The tokenization evidence concerns input encoding, not total tokens required for equivalent successful work.
Evidence (1 item)
Claims like this aren’t scored, so there is no evidence to show.
How we judged it
- Kind of claim
- Observation
- Deadline
- None given. We don’t add one.
Conditions
- appears (their words)
Where we had to interpret
- The comparison is with Opus 4.6, which the preceding passage discusses.
- The qualification 'appears to' applies to both performance and token consumption. It expresses a tentative assessment, not a firm comparative result.
- Benchmark results and token measurements can inform the assessment, but cannot supply a commitment the speaker did not make.
We don’t grade claims like this. We only check the quote and who said it.
What would settle it
A separate, firm claim specifying the tasks, comparison settings, and meaning of token consumption could be assessed.
We found 35 claims in this post. See them all.
Full record
Source and dates
Where's Your Ed At, Four Horsemen of the AIpocalypse, paragraph 26.
- Said
- We read the source
- live page, full text, public
- Evidence up to
- Checked
We read this wording on 2026-10-28. The post may have been edited after 2026-04-21.
Where it was said (1)
Said once in the posts we read.
: Where's Your Ed At, Four Horsemen of the AIpocalypse
Things only got worse with last week’s launch of Opus 4.7, which appears to have worse performance and burn more tokens.
- Where
- paragraph 26
- Published
- 2026-04-21
- We read it
- , live page
- Access
- full text, public
History
Versions
- Current: Can’t be checked. Evidence up to 2026-10-28.
What happened to this record
PublishedBy us
Published after both AI reviews and the final check passed.
Held backBy us
A reviewer said our test wasn’t fair to what was actually said.