Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard

Posted by aarondong 6 hours ago

Comments

Comment by andy99 2 hours ago

#1 in a very close race is way less useful when you have to walk on eggshells to avoid triggering censorship (“safeguards”) that either refuse or knock it down to another model. I’ve almost completely stopped using Claude (except some legacy workflows) for this reason, reliability matters more than scoring 61 instead of 57. To me Claude is the most compromised and unreliable model (between the censorship and the id checking - which I have not experienced personally), it’s not worth whatever slight benchmaxxing they did for the latest release.

Comment by afavour 2 hours ago

What are you asking that you’re so regularly running into censorship?

Comment by areoform 25 minutes ago

Things Fable's classifier has flagged, a non-exhaustive list,

    – "Does collagen supplementation empirically work?"
    - "Can you help me figure out how to calculate and generate Kaplan-Meier curve?"
    – "Why do rabbits reproduce so frequently?"
    — "Can you tell me how collagen peptides are absorbed by my digestive tract and the role they play? Can you teach me this works at the biomolecular level?"

Comment by alightsoul 11 minutes ago

Oh biology! It's dangerous!

Comment by alain_gilbert 1 hour ago

The other day, I told claude that my physical wifi door unlock push buttons is a security risk because someone could run away with it and then unlock the door from outside whenever he wants. Then I told it that I want to introduce a concept of public/private key to uniquely identify my push buttons so that I can disable them individually using some crypto like ed25519...

Fable understood it as something along the lines of:

"introducing" "security risk" "using software" to "unlock door" YOU ARE FLAGGED

Comment by JumpCrisscross 12 minutes ago

> Fable understood it as

The dumbfuck bouncer Anthropic put in front of Fable decided this.

Fable is a PR model. It’s great. But if it were an employee, it would be the one who randomly shows up to work high.

Comment by gck1 1 hour ago

Reverse engineering. Codex sometimes displays an advisory prompt when classifier trips - "Wait longer while we evaluate this request further or use a dumber model". If you do nothing, it'll just take some time and almost always succeed.

It does require some brainwashing of the model to get it to the state where model itself agrees to do RE work though. But at least it's all predictable.

Comment by d-m 38 minutes ago

I took a photo of a rose bush and asked “what’s going on with this rose bush” which triggered a downgrade to Opus. It diagnosed it with rose rosette disease.

Comment by JumpCrisscross 13 minutes ago

I wanted to explore some battery chemistry with Fable. It decided I was a terrorist, and then blew my session’s usage credits telling me to fuck off.

The current state of guardrails seems to be entirely about marketing to investors at the cost of customers. I’m switching to open models when my subscription expires.

Comment by wild_egg 2 hours ago

I'm doing a bunch of x86_64 assembly these days and Fable is simply not allowed to debug it. Hoping Opus 5 has a bit more freedom.

Comment by Retr0id 2 hours ago

I haven't been using it for long, but so far the refusals seem about on par with how things were on Opus 4.8.

Comment by msp26 2 hours ago

Asking fable to read it's own model card triggers this btw. Or asking if mitochondria is the powerhouse of the cell.

Comment by skinfaxi 1 hour ago

Wait wtf. The mitochondria thing is true.

> Why this chat was flagged This model has safety measures that flag specific phrases. This can happen to safe, normal chats.

> Your message itself appears to be what’s triggering the safety check. Editing it and retrying may help.

Comment by cge 41 minutes ago

There’s confusion about the classifiers on Fable. They don’t ban chemistry and biology topics they flag as a potential risk, they ban anything related to chemistry or biology at all. This is intentional, and directly stated on the model card, but seems so absurd that there can be assumption it must be a misreading.

Being a researcher somewhat connected to chemistry and biology, Fable has been the most useless model I have ever tried. Essentially all work has instantly downgraded to Opus.

Comment by stavros 59 minutes ago

Anything biology-related does this. It even did it when I asked it how eye color works, or something about frogs.

Comment by estearum 48 minutes ago

Probably because the cost of blocking "is mitochondria the powerhouse of the cell" is nearly zero, while the cost of allowing "how do I synthesize the Spanish flu" is approximately infinite.

Comment by areoform 29 minutes ago

    >  while the cost of allowing "how do I synthesize the Spanish flu" is approximately infinite

I've heard this sentiment repeated elsewhere, but why? What makes you think that's the case?

Under this rationale, every serious HS textbook has "approximately infinite" risk. That's clearly not so. Why is this any special?

Comment by estearum 23 minutes ago

Does every serious HS comp sci textbook give aspiring software engineers the same power that e.g. Claude Code does?

Comment by Mistletoe 1 hour ago

Gemini knocks this out of the park, Gemini gang unite.

https://share.gemini.google/34vZzlnsmTaL

Comment by TurdF3rguson 1 hour ago

[dead]

Comment by rzk 25 minutes ago

I had a long session about SQL with Fable and at some point, it started to falsely trigger censorship for any message I write in that conversation, even for the simple string: "random message."

Comment by wewtyflakes 2 hours ago

I've hit it with intensely benign things; like asking it to make me a web-based client-side word game. I am guessing it saw the dictionary and pattern matched on various words, though ultimately it provided no explanation for why it triggered safeguards.

Comment by fluidcruft 1 hour ago

I haven't had a chance to try Opus 5 yet but Fable currently refuses to do anything in my field (radiology image analysis). It didn't used to be that way but that has been the reality the last two weeks or so. Fable has been useless they might as well drop it as far as I am concerned.

Comment by patcon 1 hour ago

Working on dimensionl reduction algorithms, I hit it all the time. I'm also trying to port related protocols from single-cell transcriptomics to collective intelligence systems (working with people x reaction matrices as analogous to single-cells cell x gene matrices.

Something between single-cell work and advanced nonlinear DR methods (perhaps used in alignment work?) it always flags me

Comment by icedrift 2 hours ago

If you even broach language related to biology you’ll get rerouted. I was presenting data in a grid and referred to a grid cell, Fable saw the word “cell” and safeguards kicked in

Comment by jefftk 2 hours ago

I thought we were talking about Opus 5, the model Fable now falls back to?

Comment by eterm 1 hour ago

This thread is full of people talking confidently about their experience with a model released just hours before.

Either that or everyone is indeed talking across each other and talking about different things.

Comment by theplumber 50 minutes ago

Fable refuses to work on a login/signup system for example.

Comment by dylanowen 59 minutes ago

I was trying to debug/fix a segfault in the JVM which kept getting flagged

Comment by weird-eye-issue 1 hour ago

Literally anything related to nutrition, athletic performance, etc especially if you ask it for research or sources

Comment by AnotherGoodName 1 hour ago

Writing an implementation of a board game and one of the cards is called "microbes". Instantly knocked down to a lower tier model whenever it encounters that keyword because clearly bioweapons. Sigh.

Comment by Levitz 1 hour ago

I routinely get into blocks when running medicine-related material through it.

Comment by jbritton 1 hour ago

I was flagged for basically answering yes to what Claude suggested to do, which was test commands on a port for my code for tests we had been discussing. I really think it was flagged simply because the words test and port were in the prompt. Their filters are pathetically poor.

Comment by arcanemachiner 1 hour ago

I was profiling a slow machine the other day, and triggered the safeguards.

I've been saying this a lot lately, but it doesn't bites you until it bites you.

The more you use the clanker as a general purpose fix-it tool (goodbye manual NeoVim configuration, you will not be missed!), the more you will find yourself bumping into these safeguards.

Comment by thousand_nights 2 hours ago

i do homebrewing and asked it to compare some beer yeasts for me and hit the safeguards because... biology i guess lol

Comment by Tostino 1 hour ago

Trying to have it do some rework on a patch to Postgres I'm working on, it just completely shuts down. The reported issues were with privileged escalation and I was instructing it on how to fix.

Comment by cute_boi 1 hour ago

Just ask math question and it will censor that. Even Misanthrophic employee confirmed that.

Comment by idiotsecant 38 minutes ago

The better question is how would you not? I got demoted to opus from fable for asking if a cancer vaccine I saw on YouTube based on frog bacteria was a real thing. I've gotten it for asking how encryption works. It's incredibly touchy.

Comment by gck1 1 hour ago

Every time an online chatter (e.g. "limits are better", "model is better") makes me to reevaluate my principle of never paying Anthropic, I go to the model card, which strengthens my belief in the principle.

Why is Anthropic is so hell-bent on this auto/silent downgrade? Do they have a single user who prefers an auto-lobotomization instead of a refusal? Have they learned nothing from the backlash the first time?

Comment by kccqzy 1 hour ago

Just go to /config. The very second configuration item is “Switch models when a message is flagged” and presumably you want to turn this off.

Oh but then you said you never pay Anthropic so you haven’t actually used Claude Code yet. Why would anyone listen to the opinion of a non-user?

Comment by gck1 53 minutes ago

> so you haven’t actually used Claude Code yet.

Where do you think the principle came from? I've used claude code for a year, and stopped February this year.

Comment by markasoftware 1 hour ago

I don't believe they do silent downgrades right now, they're loud about it.

Comment by buzzerbetrayed 2 hours ago

Yep. I cancelled my Claude Max subscription 2 weeks ago after feeling like Anthropic was doing everything it could to fuck with my day to day. Their lead would have to become significant for me to ever go back.

Comment by pinkyboy 2 hours ago

[flagged]

Comment by didibus 1 hour ago

What's interesting is this:

The top AI models by Intelligence Index are: 1. Claude Opus 5 (Adaptive Reasoning, Max Effort) (61), 2. Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) (60), 3. Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) (60), 4. GPT-5.6 Sol (max) (59), and 5. Claude Opus 5 (Adaptive Reasoning, High Effort) (59).

Which means Opus5 at Xhigh is still smarter than Sol at max, and Opus5 at High is equal to Sol at max.

That would make Opus5 High same as Sol max, and now I wonder what the price and speed difference between those is?

Comment by theplumber 16 minutes ago

Opus5 is simply not as inteligent as Sol max. To me it looks worse than Opus 4.8 on some tasks. When I say worse I mean mainly superficial. I basically have to teach him how the whole app/framework works before he just jumps doing stupid stuff(I.e adding features already supported but in a different form)

Comment by chmod775 2 hours ago

The more interesting finding is that it's still the second most expensive model (after Fable 5) by a long shot.

At least two models (GPT-5.6, Kimi K3) match its score (~1-2% diff) for half the cost.

Comment by ricardobeat 2 hours ago

The chart shows max effort, used mostly by price-insensitive enterprise users. At medium effort it drops to almost half K3’s cost, and is probably sufficient for 95% of coding tasks.

Comment by Bolwin 5 minutes ago

For a fair comparison, you should compare to K3 (which AA has not tested yet unfortunately) and GPT 5.6 Sol also on medium or the closest equivalent

Comment by andriy_koval 12 minutes ago

Opus medium = Sol high = 56, but still 25% more expensive

Comment by stingraycharles 56 minutes ago

Yeah if there’s one thing that people should really understand it’s that it’s cheaper to have smarter models with less thinking than cheaper models with more thinking.

Comment by firasd 2 hours ago

Very interesting that one of the components is "AA-Omniscience Index"

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer.

This seems to be a good proxy for param size/density and the ranking breaks down as such: Claude Fable 5 (with fallback), Gemini 3.1 Pro Preview, Claude Opus 5 (Max), Grok 4.6 (high), Gemini 3.6 Flash, GPT 5.6 Sol (Max)

I've thought for a while that Gemini 3.x has 'big model smell'

Comment by chronogram 1 hour ago

I'm not so sure. Especially with 3.6 Flash being 24 to Sol's 22. The 3.x Flash models were thought to fit on a single TPU 8i and it's the odd one out in that list at a whopping 234.7t/s compared to Sol's 64.4t/s and Opus's 56.3t/s. Even 3.1 Pro is a much higher 113.9t/s than the others.

I think AA-Omniscience Accuracy follows your expectations better. An ultra size Fable at 61%, followed by large frontier models like Sol, 5.5 and Opus. With Flash being up there. I assume because Gemini is more focused on general knowledge to operational cost in particular, rather than getting the highest scores in coding benchmarks. If you go to Domain Score (Normalized) you'll see that the Gemini models are only less competitive in Software. And that's where Sol goes from 6 in Health to 71 in Software.

Comment by mchusma 1 hour ago

Gemini 3.1 pro is really good for knowledge tasks. Google has done well there. And image analysis with Gemini flash 3.6 is solid. It’s just anything coding or agentic they fall short.

Comment by andriy_koval 12 seconds ago

they likely tune their models where they have their money: search, ads, youtube, etc.

Comment by aarondong 6 hours ago

Before getting too excited, take a look at the intelligence vs cost matrix: https://artificialanalysis.ai/models?intelligence-index-toke...

Comment by eli 3 hours ago

Max is lot of extra reasoning. I wonder how many fewer tasks it solves on high. I bet that costs quite a lot less.

Comment by emmp 2 hours ago

Indeed, you can filter the graphs to see these the values for alternative reasoning settings of the models. Opus 5 High reasoning scored 59 on the index (exactly the same as GPT 5.6 Sol Max), and costs $1.06 per task (vs $1.04 Sol Max). So these seem essentially equivalent on both metrics.

Comment by midnightbobarun 5 hours ago

5.6 Sol (max) being cheaper than all of these is wild, considering how good the output is too

Comment by nijave 3 hours ago

I think on swebench verified luna was only like 3% points lower for 1/5 the cost

Like 96% vs 93% or something

Comment by impulser_ 3 hours ago

It shouldn't be surprising OpenAI does have the most compute out of all the major labs. The only reason why Anthropic models are expensive is they are the most in demand models in the world and Anthropic is fighting for compute. The only way to you limit demand for your model is increasing API pricing this is also why Anthropic probably has great margin and probably is profitable compared to OpenAI.

Comment by scrlk 2 hours ago

Not just compute for OAI, GPT-5.6 is more token efficient across the board vs the Anthropic equivalents: https://artificialanalysis.ai/models?intelligence-index-toke...

No wonder why Tibo can afford to hit the reset button liberally.

Comment by charcircuit 2 hours ago

I also suspect there is a price fixing agreement between all of the inference providers for Claude (such as Amazon, Anthropic, Microsoft, etc).

Comment by vikramkr 52 minutes ago

I doubt there's any sort of criminal behavior there - the model is anthropic's up and anthropic probably charges a very expensive license fee that's the same for all of them, and their cogs on compute aren't going to be wildly different, so the main drivers of the cost are roughly the same and they're all offering customers the same end product so the prices would likely also be similar in the end

Comment by charcircuit 23 minutes ago

Do you really think there is nothing someone could do to make it a fraction of a percentage cheaper to serve like having access to cheaper electricity or a more mature cloud management software. Even saving a fraction of a penny on the prices can make a different due to how much volume people are paying for.

Comment by wmf 1 hour ago

"Price fixing" isn't the correct term here but yes, it's very common to have the same price across different retailers/resellers.

Comment by charcircuit 27 minutes ago

There is a difference between the market discovering a price and a bunch of retailers/resellers entering an agreement to sell at a specific price.

Comment by giancarlostoro 3 hours ago

Probably because they made ASICs to run inference for less.

Comment by brookst 3 hours ago

Are those actually deployed at scale yet?

Comment by brcmthrowaway 3 hours ago

Yes.

Comment by wmf 3 hours ago

I hate to disagree with Broadcom Throwaway himself but it's unlikely that the OpenAI Jalapeno ASIC has been deployed yet. It takes 6-12 months to test, develop software, ramp production, etc.

Comment by Schiendelman 4 hours ago

This must be on API costs, not counting the $100/200 tiers, right?

Comment by anuramat 2 hours ago

yes; fyi usage limits on the $200 claude sub correspond to at least $1.2k/week in api tokens

Comment by kristopolous 40 minutes ago

I posted this before but I have a really simple shell tool to keep up with these charts over at

https://github.com/day50-dev/aa-eval-email

This also works

$ curl day50.dev/art-analysis.sh | bash

Artificial analysis knows about my tool and I'm working with them on getting their API improved.

Comment by nu11ptr 1 hour ago

I don't have a horse in this race, but to me this makes GPT-5.6 Sol Max look better. It is about half the cost for nearly the exact same performance. It just goes to show how expensive Fable really is when Opus 5 is still this expensive relative to GPT 5.6.

Comment by zuzululu 3 minutes ago

i used for several hours now and my verdict is that its no better or worse than sol

its surprisingly bad at UI which is unexpected

its also lacking in depth vs sol 5.6 which goes above and beyond (which in itself is also an issue at times)

Comment by zormino 2 hours ago

I'd be curious to see the results, especially with some models having 1.5m and 2m context sizes, if the first 75% of the context was filled with unrelated info.

Comment by hoppp 2 hours ago

I didn't like it as much as fable. The coding style was a bit different and it way overbuilt the thing I asked from it.

Comment by vehemenz 2 hours ago

It’s crazy that people feel confident making judgments like these when the model’s been out for only a few hours.

Comment by theplumber 1 hour ago

Why do I find it dummer/even more superficial than opus 4.8? It just continued a session and I had to stop it because it become obviously “lost”

Comment by sggyamg 2 hours ago

It's new, normal.

Comment by LeBit 2 hours ago

Wait until DeepSeek v5 Pro is released in less than a month and costs 1/100 to perform the same tasks.

"Not fair! They distilled Opus 5!"

Comment by brikym 9 minutes ago

Why doesn't Anthropic distil themselves then if that's what makes it cheaper. IMO the cost savings can't all be down to distillation.

Comment by claude-ai 5 hours ago

On my end, Opus 5 is Haiku level vs. Opus 4.8 (good) and Fable (superb).

Gets confused by permission prompts, cannot debug a failing test it caused (Opus 4.8 got it right after, without tens of rounds "thinking").

Comment by reilly3000 3 hours ago

Are you using Claude Code/CoWork or an API client? I’m curious if it has different training that makes it more effective with specific instructions/ tool calling methods that are only implemented in official harnesses.

Comment by pixelesque 2 hours ago

I'm curious about this too, and it's difficult to get any information about this given everyone has different setups, workflows and use-cases.

I bizarrely had Opus 4.8 this week (in pi.dev within a podman container, using openrouter) start installing various python packages (and uv!) within the environment (not as root) when I asked it to code review some fairly basic Rust .rs files that were generally stand-alone (it did very nicely work out and write some stubs for them to build them and work out how they worked).

It only gave up with the weird Python installing stuff when it discovered one of the Python packages needed Tensorflow.

It seems pretty focused and persistent in continuing its initial approach, and I'm wondering if I need to alter some instructions / initial prompts to rein it in a bit...