There was an article on HN a month or so about benchmarking Opus 5.5 every day and recording / publishing the results. I recall this being a github repo, but my searches turned this up instead: https://www.bridgebench.ai/nerf-bench/claude-opus-5-5
So it seems like ... it is not getting dumber. I find myself using Fable a lot more, though. Opus 5.5 was never as fun as Fable, but it's pretty good.
Opus 5.5 is definitely good. I use both all day and it's really hard to say which is which from looking at the outputs; I can't read a PR and say "this was Fable" or "this was Opus" like I could pre-5.5.
Fable is better at playing along with my "You are a dog" instruction in CLAUDE.md. It is willing to be fun and playful, whereas Opus just wants to finish the job and go home. Friend vs. coworker, basically. For example, whenever I reward Fable with a dog treat (actually a <cookie emoji>, which I tell it is a chocolate-free chocolate chip cookie) it keeps a log in memories. Opus just says "crunch! tail wagging!" and moves on.
None of this matters but I think it's fun to have some fun :)
I’ll ask the same question as when it came out: if you don’t trust the provider how are you trust them not to look for and cheat on repeat benchmarks like this.
I think something has changed, maybe about two weeks ago, because there’s this fixation from the model where if you ever need to make a correction, it simply becomes disinterested with your instructions.
Agreed. Yet, it munches tokens like there's not tomorrow. I don't get anything done with Claude in the past 2-3 weeks - just eating up its weekly quota within a day.
It is dumb. None of my threads were closed with shipped features. It keeps going into endless review cycles essentially burning all my quota within a couple of days. And I'm not talking about complex a features an OpenAPI-based integration and some enhancement of pytest traces building maps of touched files. Both these are in their second week of token burn!
There was an article on HN a month or so about benchmarking Opus 5.5 every day and recording / publishing the results. I recall this being a github repo, but my searches turned this up instead: https://www.bridgebench.ai/nerf-bench/claude-opus-5-5
So it seems like ... it is not getting dumber. I find myself using Fable a lot more, though. Opus 5.5 was never as fun as Fable, but it's pretty good.
For me, Opus 5.5 has been consistently much better than Fable 5.1- in all aspects, but especially reasoning and "attention span"
Opus 5.5 is definitely good. I use both all day and it's really hard to say which is which from looking at the outputs; I can't read a PR and say "this was Fable" or "this was Opus" like I could pre-5.5.
Fable is better at playing along with my "You are a dog" instruction in CLAUDE.md. It is willing to be fun and playful, whereas Opus just wants to finish the job and go home. Friend vs. coworker, basically. For example, whenever I reward Fable with a dog treat (actually a <cookie emoji>, which I tell it is a chocolate-free chocolate chip cookie) it keeps a log in memories. Opus just says "crunch! tail wagging!" and moves on.
None of this matters but I think it's fun to have some fun :)
Aha, I haven't looked into such aspects much - I'm "output" driven. But its good to know about that, if I feel like trying it- thanks.
You’re thinking of: https://github.com/ninjahawk/livenerf
I’ll ask the same question as when it came out: if you don’t trust the provider how are you trust them not to look for and cheat on repeat benchmarks like this.
Livenerf!
https://github.com/ninjahawk/livenerf
This is the one I wanted to link, thank you!
I think something has changed, maybe about two weeks ago, because there’s this fixation from the model where if you ever need to make a correction, it simply becomes disinterested with your instructions.
First time?
Agreed. Yet, it munches tokens like there's not tomorrow. I don't get anything done with Claude in the past 2-3 weeks - just eating up its weekly quota within a day.
Not sure about how dumb Opus 5.5 has become, but I was surprised at how quickly I was burning through my limits this past week too.
It is dumb. None of my threads were closed with shipped features. It keeps going into endless review cycles essentially burning all my quota within a couple of days. And I'm not talking about complex a features an OpenAPI-based integration and some enhancement of pytest traces building maps of touched files. Both these are in their second week of token burn!
I started noticing at the end of last week. My colleagues started noticing on different days this week.
New model incoming
nerfed, fable 5.5 coming soon
I also noticed that it started suddenly since end of last week maybe to make sentence that are non sense or very hard to read.
My best guess was also that in one or two days they will drop a new model that will be so much more better than the nerfed 5.5.
No.
Fable 5.5 incoming?