@vasuman: Opus 5 is token-hungry and incredibly stupid. Under-explains its changes, over-indexes on meaningless words. Avoid.
Summary
A user criticizes Opus 5 as token-hungry and unintelligent, advising avoidance due to its poor explanation of changes and overemphasis on insignificant words.
View Cached Full Text
Cached at: 07/31/26, 12:45 AM
Opus 5 is token-hungry and incredibly stupid.
Under-explains its changes, over-indexes on meaningless words.
Avoid.
Similar Articles
Why does Opus 5 feel worse to work with?
An opinion piece arguing that Anthropic's Opus 5, while more capable by benchmarks, feels worse to work with than earlier models because it makes assumptions instead of asking for clarification, likely due to benchmark-driven training.
Sonnet 5.5 is worse than Opus 5.5 but costs more?? Sonnet costs the same as Fable 5.1? The reason: Sonnet 5.5 is waaaay less token efficient. Don't be fooled, continue using Opus!
The post compares Sonnet 5.5 and Opus 5.5, stating that Sonnet 5.5 is less token-efficient and more costly, advising users to continue using Opus.
Anthropic's Opus 5 is about token efficiency, not a capability leap
Anthropic released Opus 5, focusing on token efficiency and cost reduction rather than a major capability leap, offering performance close to Fable at half the cost.
@thermalpastor: The scariest thing about Opus 5.5 is that it goes back to fill in the arm realising the lines were dotted.
The tweet compares Opus 5.5's performance to Astra on a task, noting it performs better but uses 10x more tokens and draws faster.
@paul_cal: Opus 5.5 keeps getting stuck on bad waits. Multiple times I've had whole 5+ hr workstreams paused bc 1 intermediate job…
A user criticizes Opus 5.5 for frequently pausing workstreams due to intermediate job failures, contrasting it with the better reliability of Codex 5.5+.