Opus 4.6 1m has degraded performance and now acts dumber than Sonnet 3.5
Preflight Checklist
- [x] I have searched existing issues for similar behavior reports
- [x] This report does NOT contain sensitive information (API keys, passwords, etc.)
Type of Behavior Issue
Claude modified files I didn't ask it to modify
What You Asked Claude to Do
I do not know what is going on but ever since around the time the opus models moved to the 1 million token context window I have found the models almost unusable. The change is night and day. This si not context bloat this is very simple prompts and tasks with a freshly cleared context and I am not able to trust anything going on anymore. I just had Opus reverse it's own decision 4 times in a row and search the web 2 times with a drizzle thing for on conflict do update and it literally could not stop tearing everything down and rebuilding it using raw sql and using drizzle after being told use drizzle and looking up the exact things to use ???????
Another case, II literally say hey we are using too small of a batch size on these upserts, increase the batch size and it claims to do this. An Hour later I find out it batch inserted one column's dat form the whole table and for the rest of the table was doing sequential single upserts per record???? Like WHAT? This is obviously retarded behavior.
The other day I literally couldn't get it to widen a dialogue component. A shadcn dialogue component??? I said make that dialogue wider and it literally cannot or would not do it, we are talking about things Claude sonnet 3.5 used to do and do them faster!!!
This is a large enough issue that if it does not improve very VERY VERY soon I am leaving Anthropic I feel like I am just getting ripped off at this point.
What Claude Actually Did
Literally failed to follow simple single line instructions as listed above
Expected Behavior
Behavior and intelligence equal to or greater than previous models and releases, this is a HUGE degradation in performance on basically every metric
Files Affected
Permission Mode
Accept Edits was ON (auto-accepting changes)
Can You Reproduce This?
Haven't tried to reproduce
Steps to Reproduce
This is not exactly reproducible its a general lack of performance in every task over the last 3 weeks or so. Simple things Claude used to finish in 2 seconds are now not done correctly and take longer. I am filing this to start signaling that there is something going wrong, something is deeply incorrect about the way we are currently interacting with Opus, it feels dumber than Claude Sonnet 3.5 most of the time.
Claude Model
Opus
Relevant Conversation
Impact
Critical - Data loss or corrupted project
Claude Code Version
v2.1.81
Platform
Anthropic API
Additional Context
_No response_
6 Comments
Found 3 possible duplicate issues:
This issue will be automatically closed as a duplicate in 3 days.
🤖 Generated with Claude Code
similar experience here on 2.1.81
agree with the timelines. This doesn't feel like Opus anymore, reminded me of the earlier days when we asked Chatgpt to vibe code
You should switch down to Sonnet instead of Opus. Give it a try, I think it will be better for your work. Better only though, it's still really bad in reality.
For sure tried this, for some things it's good but overall I feel like something is going wrong like last time when Anthropic had this issue and they didn't admit it until months later, I think the same thing is going on again. If I remember correctly they were incorectly routing requests to the wrong API, I forget the details.
This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.