Artificial Analysis: The Independent LLM Analysis House — with George Cameron and Micah Hill-Smith

This is kind of a full circle moment for us in a way, um-

Yeah

... 'cause the, like, first time Artificial Analysis got mentioned on a podcast was you and Alessia on Latent Space.

Amazing.

Which was January 2024.

I, I don't even remember doing that. But yeah. It was, it was very influential to me. Um, yeah, I'm looking at AI News for Jan 17 or Jan 16, 2024. Uh, I said, "This gem of a models and host comparison site was just launched," and, uh, and then I put in a few screenshots.

And I said, um, "It's an independent third party. It clearly outlines the quality versus throughput trade-off."

Mm-hmm.

"And it breaks out by model and hosting provider." Uh, I did give you shit for missing Fireworks.

Uh, how do you have a model benchmarking thing without Fireworks? But you had Together, you had Perplexity, and, uh, I think we just started chatting there. Welcome, George and Micah, uh, to Latent Space. You've- I've been following your progress.

Congrats on a, an amazing year. You guys have really come together to be the presumptive new Gartner of AI. Okay, how do I pay you? Let's get right into that. How do you make money?

Um, well, very happy to talk about that. So it's been a, like, big journey the last couple of years. Artificial Analysis is gonna be two years old in January 2026-

Mm-hmm

... which is pretty soon now. We first run, like, the website for free, obviously, and give away a ton of data to help developers and companies navigate AI and make decisions about models, providers, technologies across the AI stack for building stuff.

We're very committed to doing that, intend to keep doing that. We have, along the way, built a business that is working out pretty sustainably. We've got just over 20 people now and two main customer groups. So we want to be who enterprise look to for data and insights on AI, so we want to help them with their decisions about models and technologies for building stuff.

And then on the other side, we do private benchmarking for companies throughout the AI stack who build AI stuff. So no one pays to be on the website. We've been very clear about that from the very start, 'cause there's no use doing what we do unless it's independent AI benchmarking.

Yeah.

Um, but turns out a bunch of our stuff can be pretty useful to companies building AI stuff.

And is it like, "I'm a Fortune 500, I need advisors on objective analysis," and I call you guys, and you pull up a custom report for me, you come into my office and give me a workshop? What, what, what kind of engagement is that?

So we have a benchmarking insight subscription which looks like standardized reports that cover key topics or key challenges enterprises face when looking to understand AI and choose between all the technologies. And so, for instance, one of the report is a model deployment report, how to think about choosing between serverless inference, managed deployment solutions, or leasing chips and running inference yourself is, is, is an example kind of decision that big enterprises, uh, face, and it's hard to, hard to reason through.

Like, this AI stuff is, is really new to, to everybody. And so we try and help with our reports and insight subscription companies navigate that. We also do custom private benchmarking, and, um, so that's very different from the public benchmarking, um, that we publicize, and there's no commercial model around that.

For b- for private benchmarking, we'll at times create benchmarks, run benchmarks to specs that enterprises want. And we'll also do that sometimes for AI companies who have built things, and we help them understand what they've built with private benchmarking, um, you know, through the expertise mainly that we've developed through trying to support everybody, uh, publicly, uh, with our public benchmarks.

Yeah. Uh, let's talk about tech stack, uh, behind that. But okay, I'm gonna rewind, uh, all the way to when you guys started this project. Uh, you were all-all the way in Sydney then?

Yeah, Syd- well, Sydney, Australia for me. George was in SF, but-

Yeah

... he's Australian, but had moved here already.

Yeah. And, um, I remember I had the, the Zoom call with you. Um, what was the impetus for starting Artificial Analysis in the first place? You know, you started with, uh, public benchmarks, and so let's, let's start there, and we'll go to the private stuff.

Yeah. Why don't we even go back a little bit to, like, why we, you know, thought that it was, that it was needed?

Yeah.

The story kind of begins, like, in 2022, 2023. Like, both George and I have been into AI stuff for quite a while. In 2023 specifically, I was trying to build a legal AI research assistant. So it actually worked pretty well for, for, for its era, I would say, but was finding that the more you go into building something using LLMs, the more each bit of what you're doing ends up being a benchmarking problem.

So had, like, this multi-stage algorithm thing, trying to figure out what the minimum viable model for each bit was, trying to optimize every bit of it. As you build that out, right, like, you're trying to think about accuracy, bunch of other metrics, and performance and cost.

And mostly just no one was doing anything to independently evaluate all the models and certainly not to look at the trade-offs for speed and cost. So we basically set out just to build a thing that developers could look at to see the trade-offs between all of those things measured independently across all the models and providers.

Honestly, it was probably meant to be a side project when we first started doing it. Like, we didn't, like, get together and say, like, "Hey," like, "we're gonna, um, stop working-

Yeah

... on other stuff," and, like, "This is gonna be our main thing."

When I first called you, I think, uh, you, you hadn't decided on starting a company yet.

That's actually true.

No-

I don't even think we'd paused, like, like George hadn't quit his job. I hadn't quit working on my own legal AI thing. Like, it, it was genuinely a side project.

Yeah.

Yeah. Um-

We built it because we needed it as people building in the space, and thought, "Oh, other people might find it useful too, so we'll buy a domain and link it to the Vercel deployment that, that, that we had."

Yeah.

We, we, and, and, and, and, and, and tweet about it, and but very quickly it started getting attention. Thank you, Swyx, for, I think, doing an initial retweet and spotlighting it there, this project that, that we released. And then very quickly, though, it, it was useful to others, but very quickly it became more useful as the number of models, uh, released accelerated.

Uh, we had Mixtral 8×7B, and it was a key-

Oh, that's a fun one

... yeah, like a, a, a open source model that really changed the landscape and opened up people's eyes to other serverless inference providers, and thinking about speed, thinking about cost. And so it became more useful, um, quite quickly.

Yeah. What I love talking to, to people like you who sit across the ecosystem is, well, I have theories about what people want, but you have data, and that's, uh, obviously more, more relevant. Uh, but I want to stay on the origin story a little bit more.

Um, when you started out, I would say I think the, the status quo at the time was every paper would come out, and they would report their numbers versus competitor numbers, and that's basically it. And, uh, I remember I did the legwork.

I think, I think everyone has some version of Excel sheet or s- uh, Google Sheet where you just, like, copy and paste the numbers from every paper and just post it up there, and then sometimes they don't line up because they're independently run.

And so your numbers are gonna look, uh, better, uh, than the... Or, or y- your reproductions of other people's numbers are gonna look worse 'cause you don't hold their n- models correctly or whatever, whatever the, the excuse is.

I think then Stanford Helm, Percy Liang's project, would also have some, some of these numbers, and I don't know if there's any other source that you can cite. The way that if I were to start Artificial Analysis at the same time you guys started, I would have used EleutherAI's, um, eval framework, uh, harness.

Yep, yep. That was some cool stuff. Um, at the end of the day, right, running these evals, it's like if it's a simple Q&A eval, all you're doing is asking a list of questions and checking if the answers are right, which shouldn't be that crazy.

But it turns out there are an enormous number of things that you've got to control for. And I mean, back when we started the website, like, one of the reasons why we were, we realized that we had to run the evals ourselves and couldn't just take, um, results from the labs, was just that they would all prompt the models differently.

And when you're competing over a few points, then you can, um, pretty easily get-

You can put the answer into the model.

I, I mean, yeah.

Into the prompts, yeah.

That, that in the extreme. And, like, you get crazy cases like back when, um, Google did Gemini 1.0 Ultra and needed a number that would say it was better than GPT-4 and, um, like, constructed, um, I think never published, like, chain-of-thought examples, 32 of them in every topic in MMLU to-

Right

... run it to get the score. Like, there are so many things that you, you could-

They never shipped Ultra, right?

Um-

That's the, that's the one that never made it out

... not, not widely publicly, no.

Yeah, yeah, yeah.

I mean, it, it, I'm sure it existed. But yeah, so we were pretty sure that we needed to run them ourselves and just run them in the same way across all the models.

Yeah.

And we were, we were also dead certain from the start that you couldn't look at those in isolation. You needed to look at them alongside the cost and performance stuff.

Yeah. Okay, a couple c- technical questions. I mean, so obviously I also thought about this, and I didn't do it because cost.

Yep.

Did you, did you not worry about cost? Were you funded already? Clearly not, but, you know.

No, we, we... Well, we definitely weren't at the start. So, like, um, I mean, we were paying for it personally at the start.

There's, there's a lot on here.

So, well, the numbers weren't-

Yeah.

... nearly as bad a couple of years ago. So we, like, certainly, um, like, incurred s- some costs, but we were probably in the order of, like, hundreds of dollars of spend across all the benchmarking that we were doing-

Okay, so nothing

... at the start.

Yeah, yeah.

It was, like, kind of fine.

Yeah, yeah.

These days, that's gone up an enormous amount for a bunch of reasons that we can talk about. Um, but yeah, it wa- it wasn't that bad 'cause if, you can also remember that, like, the number of models that we were dealing with was hardly any, and the complexity of the stuff that we wanted to do to evaluate them was a lot less.

Like, we were just asking some Q&A-type questions. And then one specific thing was for a lot of evals initially, we were just, like, sampling an answer directly without letting the models think. We weren't even doing chain-of-thought stuff initially, and that was the most useful way to get some results initially.

Yeah. And so for, if, for people who haven't done this work, literally parsing the responses is a whole thing, right?

Yeah.

Like, because sometimes the models, the models can answer any way they f- feel fit, and sometimes they actually do have the right answer, but they just return the wrong format, and they will get a zero for that unless you fit, work it into your parser, and that-

Yeah, depending how you grade it

... involves more work.

Yeah.

And so there, I mean, but there's an open question whether you should give it points for not f- following your instructions on the format, so.

It depends what you're looking at, right?

Yeah.

'Cause you can, if you're trying to see whether or not it can solve a particular type of reasoning problem, and you don't want to test it on its ability to do answer formatting at the same time, then you might want to use an LLM as answer extractor approach to make sure that you get the answer out no matter how it answered.

But these days it's mostly less of a problem. Like, if you instruct a model and give it examples of what the answer should look like, it can get the answers, um, in your format, and then you can do, like, a simple regex.

Yeah, yeah. And then, uh, there's other questions around, I guess sometimes if you have a multiple choice question, sometimes there's a bias towards the first answer, so you have to randomize the responses.

Yep.

All these nuances you on-

Totally

... like, once you dig into benchmarks, you're like, "I don't know how anyone believes the numbers on all these things."

Yeah.

'Cause it's so, it's so dark magic. It's-

You've also, yeah, got, like, the, um- Uh, different degrees of variance and different benchmarks, right?

Yeah.

So if, if you, if you run four-question multi-choice on a modern reasoning model at the temperature suggested by the labs for their own models, the variance that you can see on a four-question multi-choice eval is pretty enormous if you only do a single run of it and it has a small number of questions es- especially.

So, like, one of the things that we do is run an enormous number of all of our evals when we're developing new ones and doing upgrades to our intelligence index to bring in new things, so that we can dial in the right number of repeats, so that we can get to the 95% confid- confidence intervals that we're comfortable with, so that when we pull that together, we can be confident in intelligence index to at least as tight as, like, a plus or minus one at a 95% confidence.

Yeah. And again, that just adds a straight multiple to the cost. And you just-

Oh, yeah.

Yes.

Yeah, yeah.

Right?

So that's one of many reasons- ... that cost has gone up, uh, a lot more than linearly over the last couple of years.

We, um, we report a cost to run the Artificial Analysis Intelligence Index on our website.

Mm-hmm.

And currently that's assuming one repeat-

Okay.

Yeah

... um, in terms of how we re- report it, because we want to reflect, uh, a, a bit about the weighting of the index. But, um, but our cost is actually a lot higher than what we, uh, report there because of the repeats.

Yeah. Yeah, yeah. A- and probably this is true, but just checking, they, you don't have any special deals with the labs. They don't, they don't discount it. You, you just pay out of pocket or out of your, your sort of customer funds.

Oh, the, the, the, there is, there is a mix.

Okay.

So we-

So, so the, the, the issue is that sometimes they may give you a special endpoint, which-

Ah, 100%. Yeah, yeah, yeah.

Okay.

Ex- exactly. So we, uh, um, laser focus, like, on everything we do on having the best independent metrics and making sure that no one can manipulate them in any way. There are quite a lot of processes we've developed over the last couple of years to make that true for, like, with the one you bring up, like, right here of the fact that if we're working with a lab, if they're giving us a private endpoint to evaluate a model, that it is totally possible that what's sitting behind that black box is not the same as they serve on a public endpoint.

We're very aware of that. We have what we call a mystery shopper policy. And so-- And we're totally transparent with all the labs we work with about this, that we will register accounts not on our own domain and run both intelligence evals and performance benchmarks-

Yeah, that's the job

... without them being able to identify it, and no one's ever had a problem with that. 'Cause, like, a thing that turns out to actually be quite a good factor in the industry is that they all want to believe that none of their competitors could manipulate what we're doing either.

That's true. I never thought about that. I've been in a database, data industry prior, and there's a lot of shenanigans around benchmarkings, right?

Yeah.

So I'm just kind of going through the mental laundry list. Did I miss anything else in, in that, in this category of shenanigans?

The danger of shenanigans. I mean, okay, the, the, the, the biggest one, like, that I'll bring up, like, is more of a conceptual one actually than, like, direct shenanigans. It's that the things that get measured become things that get targeted by labs-

Good hard work

... what they're trying to build, right? Exactly. So that doesn't mean anything that we should really call shenanigans. Like, I'm not talking about training on test set, but if you know that you're gonna be graded on a particular thing, if you're a researcher, there are a whole bunch of things that you can do to try to get better at that thing that preferably are going to be helpful for a wide range of how actual users want to use the thing that you're building, but will not necessarily do that.

So, for instance, the models are exceptional now at answering competition maths problems. There is some, uh, relevance of that type of reasoning and that type of work, um, to, like, how we might use modern coding agents and stuff.

Um, but it's clearly not one for one. So the thing that we have to be aware of is that once an eval becomes the thing that everyone's looking at, scores can get better on it without there being a reflection of overall generalized intelligence of these models getting better.

That has been true for the last couple of years, it'll be true for the next couple of years. There's no silver bullet to defeat that other than building new stuff to stay relevant and measure the capabilities that matter most to real users.

Yeah. And we'll, we'll cover, we'll cover some of the new stuff that you guys are building as well, uh, which is cool. Like, you, you used to just run other people's evals, but now you're coming up with your own, and I think obviously that is a, a necessary path once you're at the frontier.

You've exhausted all the existing well-known ones. I think the next point in history that I have for you is AI Grant, that you guys decided to, to join-

Yeah. Yeah, sure, yeah

... and, and move here. What's, what was it like? I think you, you were in, like, batch two?

Batch four.

Batch four? Okay.

I mean, it was great. Nat and Daniel are obviously great, and it's a really cool group of companies that we were in AI Grant alongside. It was really great to get Nat and Daniel on board. Obviously, they've done a whole lot of great work in the space with a lot of leading companies, and we're extremely aligned with the mission of what we were trying to do.

Like, we're not quite typical of, like, a lot of the other AI startups that they've invested in, and they were very much here for the mission of what we want to do.

Did they s- say any advice that really affected you in some way? Or, like, were one of the events very impactful?

That's an interesting question. I, I mean, I remember fondly a bunch of the, um, speakers who came into Fireside Chats at AI Grant.

Which is also, like, a crazy list.

Yeah. Oh, totally.

Yeah.

Yeah, yeah. Yeah.

Yeah. I, I, I-- There was something about, um, you know, speaking to Nat and Daniel about the challenges of, of, of working through a startup and just working through the questions that don't have, like, clear answers and how to, to work through those kind of methodically, um, and just, like, work through the hard decisions.

Uh, and they've been great mentors-

Yeah

... to, to us as w- as we've built Artificial Analysis. Another benefit for us was that other companies in the batch and other companies in AI Grant- ... are pushing the capabilities of, of, of what AI can do at this time.

And so being in contact with them, making sure that Artificial Analysis is, is useful to them, has been fantastic for, for supporting us in working out how, how should we build out Artificial Analysis to continue to being, uh, useful to those, like, you know, building on AI.

I think s- to some extent, I'm mixed opinion on that one because to some extent, your target audience is not m-

People in AI Grants who are obviously at the frontier. Yeah, to de- to some, to some extent. But then, so a, a lot of what the AI Grant companies are doing is, um, taking capabilities coming out of the labs and trying to push the limits of what they can do across the entire stack for building great applications, which actually makes some of them pretty archetypical power users of artificial analysis.

Some of the people with the strongest opinions about what we're doing well and what we're not doing well and what they, uh, wanna see next from us. 'Cause when you're building any kind of AI application now, chances are you're using a whole bunch of different models, you're maybe switching reasonably frequently for different models in different parts of your application to optimize what you're able to, to do with them at an accuracy level and to get better speed and cost characteristics.

So for many of them, you know, they're, um, like, not commercial customers of ours, like, we don't charge for all our data on the website, but they are absolutely some of our power users. So let's talk about just the, the, the evals as well, right?

Like, you see, you start out from the ge- the general, like, MMLU and GPQA stuff. Um, what's next? How do you, how do you sort of build up to, um, the overall index, what was in V1, and how did you evolve it?

Okay. So first just, like, background, like, we're talking about the Artificial Analysis Intelligence Index. Mm. Which is our synthesis metric that we pull together currently from 10 different eval data sets to give what we're pretty confident is the best single number to look at for how smart the models are.

Obviously doesn't tell the whole story, that's why we publish the whole website of all the charts to dive into every part of it and look at the trade-offs, but best single number. So right now it's gotten a, a bunch of Q&A type data sets that have been very important to the industry, like a couple that you just mentioned.

It's also got a couple of agentic data sets. It's got our own long context reasoning data set and some other use case focused stuff. As time goes on, the things that we're most interested in that are gonna be important to the capabilities that are becoming more important for AI, what developers are caring about, are gonna be first around agentic capabilities.

So surprise, surprise, we're all loving our coding agents, and how the model's gonna perform like that and then do similar things for different types of work are really important to us. The linking to use cases, to economically valuable use cases are extremely important to us.

And then we've got some of these, um, things that the models still struggle with, like working really well over long contexts that are not gonna go away as specific capabilities and use cases that we need to keep evaluating.

Mm-hmm. And but I guess one thing I was driving was, like, the V1 versus the V2. Oh, yeah. And how that evolves over time. Like, our, like, how we've changed the index to- Yes ... where we are. Yeah, I think that reflects on, well, the change in the industry, right?

Yep. So that's a nice way to tell that story. Well, V1 would be completely saturated right now- ... by almost every model coming out because doing things like writing the Python functions in HumanEval is now pretty trivial. It's easy to forget actually, I think, how much progress has been made in the last two years.

Like, we, we obviously play the game constantly of, like, the today's version versus last week's version and the week before, and all of the small changes and the horse race between the current frontier and the who has the best, like, smaller than 10 B model, like, right now this week, right?

And that's very important to a lot of developers and people in, especially in this particular city of San Francisco. But when you zoom out, a couple of years ago, literally most of what we were doing to evaluate the models then would all be 100% solved by even pretty small models today, and that's been one of the key things, by the way, that's driven down the cost of, um, intelligence at every tier of intelligence.

We can talk about more in a bit. So V1, V2, V3, we made things harder. We covered a wider range of use cases, and we tried to get closer to things developers care about as opposed to, like, just the Q&A type stuff that MMLU and GPQA represented.

Yeah. I don't know if you have anything to add there. Uh, or we could just go right into showing people the benchmark and, like, clicking around and ask- asking questions about it. Yeah, let's do it. Okay. This will be a pretty good way to chat about a few of the new things we've launched recently.

Yeah, and I think a little bit about the direction that we wanna take it, and we wanna push benchmarking. Currently, the Intelligence Index and, and, and evals focus a lot on kind of raw intelligence, but we kind of want to diversify how we think about intelligence and, uh, we can, we can talk about it, but kind of new evals that we've kind of built, um, and partnered on focus on, uh, topics like hallucination, and we've got a lot of topics that I think are not covered by the current eval set that should be.

Mm-hmm. Uh, and, and so we want to bring that forth. But before we get into that, um- And so, so for listeners- Mm-hmm ... just as a timestamp, right now on number one is Gemini 3 Pro High, then followed by Claude Opus at 70, uh, just 5.1 High, you don't have 5.2 yet, uh, and Kimi 2 Thinking.

Wow, still hanging in there. So those, those are the top four. That will date this podcast quickly. Yeah, yeah. I mean, I, I, I love it. I love it. No, no, 100%. Let's mark the time stamps. Yeah. Look back this time next year and go, "How cute."

Yep. Like Totally. A quick view of that is, okay, there's a lot. I love this chart. Yeah. This is, this is such a favorite, right? Yeah. Um, and almost every talk that George or I give at conferences and stuff, like, we always put this one up first to just talk about situating where we are in this moment in history.

This, I think, is the, the visual version of what I was saying before about the zooming out and remembering how much progress there's been. If we go back to just over a year ago, before o1, before Claude Sonnet 3.5, we didn't have reasoning models or coding agents as a thing, and the game was very, very different.

If we go back even a little bit before then, we're in the era where when you look at this chart, like, OpenAI was un- untouchable for well over a year. And I mean, you would remember that time period well of, like, there being very open questions about whether or not AI was going to be competitive.

Mm-hmm. Like, full stop. Whether or not- OpenAI would just run away with it, whether we would have the, a few frontier labs and no one else would really be able to do anything other than consume their APIs. I am quite happy overall that the world that we have ended up in is one where-

Multi-model. Yeah

... absolutely, and strictly more competitive every quarter over the last two years.

Yeah. This year has been insane.

Yeah. You can see it. Uh, this chart with everything added is hard, hard to read currently. Um-

Yeah

... there's so many dots on it, but I think it reflects a little bit, you know, what, what we felt like-

Is this a-

... how crazy it's been

... w- why 14, uh, as the default? Is that a manual choice? 'Cause you got ServiceNow in there. There are-

Mm-hmm

... you know, less, less traditional names.

Yeah, it's models that we're kind of highlighting by default in our charts, in our intelligence index-

Okay

... is where the-

You just have a manually curated list of stuff?

Yeah, that's right. But, um-

Yeah

... something that I d- actually don't think every, uh, Artificial Analysis user knows is that you can customize our charts and, and choose what, uh, what models are, are, are highlighted.

Oh, yeah. Super important. Yeah, yeah.

Um, and so if we, you know, take off a few names, it gets a little easier to-

Yeah, yeah

... a little easier to read.

Yeah, totally. Yeah, but y- you can... Uh, I love that you can see the o1 jump. Look at that.

Mm.

September 2024.

And the DeepSeek jump.

That is ...

Yeah.

Which got close to-

Ah

... OpenAI's leadership.

They were so close.

I think, yeah, we, we remember that moment. Ar- around this time, uh, last year, actually.

Yeah, yeah. Agree.

Yeah. Well, couple of weeks. It was, it was Boxing Day in New Zealand, uh- ... when, when DeepSeek V3 came out, and I... Like, we'd been tracking DeepSeek and a bunch of the other global players that were less known over, like, the second half of 2024, and had run evals on the earlier ones and stuff.

I, I very distinctly remember Boxing Day in New Zealand. I, 'cause I was with family for Christmas and stuff, running the evals and getting back result by result on DeepSeek V3. Um, so this was, like, the, the first of their V3 architecture, the 67 1B MoE.

Um, and we were very, very impressed. Like, that was the moment where we were sure that DeepSeek was no longer just one of many players, but had jumped up to be a thing. Um, the world really noticed when they followed that up with the RL working on top of V3 and R1 succeeding, like, a few weeks later.

Um, but the groundwork for that absolutely was laid with a, like, just extremely strong base model, completely open weights, that we had as the best open weights model on Boxing Day last year.

Yep. Boxing Day is the, the day after Christmas for, for those not-

True.

Not familiar. Yeah.

I mean, I'm, I'm from Singapore. A lot of us remember Boxing Day, uh, for, for a different reason, for the tsunami that happened.

Oh, of course. Yeah.

Yeah. So I was... Yeah, yeah. But that was a long time ago. So, yeah. So this is the, the rough, uh, pitch of AQI. Uh, or is it AQI or A- AII?

AII.

Okay.

So good, good memory, though. So-

I don't know. I got used to it

... once, once upon a time we did call it Quality Index.

Okay.

Um, and we would talk about, um, quality, performance, and price, but, um, we changed it to Intelligence-

Yeah. There's been a few naming changes. We added hardware benchmarking to the site-

Right

... and, um, so benchmarks at a, at a kind of system level. And so then we changed our throughput metric to, we now call it output speed, and then throughput makes sense at a system level, so

Got it. Got it

... took that name.

Uh, take me through more charts today. What should, what should people know? You know, obviously the way you look at the site is probably different than how a beginner may look at it.

Yeah. It's, that, that's fair. We can... There's, there's a lot of fun stuff to dive into. Um, maybe so we can head past all the, like, we've, like, we have lots and lots of evals and stuff. Um, the interesting ones to talk about today that'd be great to bring up are, like, a few of our recent things, I think, um, that probably not many people will be familiar with yet.

So first one of those is our Omniscience Index. So this one is a little bit different to most of the intelligence evals that we run. We built it specifically to look at the embedded knowledge in the models and to test, um, hallucination by looking at when the model doesn't know the answer, so not able to get it correct, what's its probability of saying, "I don't know," or giving an incorrect answer.

So the metric that we use for omniscience goes from negative 100 to positive 100 because we're simply taking off a point if you give an incorrect answer to the question. We're pretty convinced that this is an example of where it makes most sense to do that because it's strictly more helpful to say, "I don't know," instead of giving a wrong answer to a factual knowledge question.

And one of our goals is to shift the incentive that evals create for, um, models and the labs creating them to get higher scores. And almost every eval across all of AI up until this point, it's been graded by simple percentage correct as the main metric, the main thing that gets hyped, and so you should take a shot at everything.

There's no incentive to say, "I don't know." So we did that for this one here.

I think there's a general f- uh, field of calibration as well, like the confidence in your answer versus the-

Yeah

... rightness of the answer.

Yeah. Completely agree.

Yeah. On that, and one reason that we didn't do that is be- uh, or put that into this, uh, index, is that we think that the, the way to do that is not to ask the models how confident they are.

I don't know. Maybe-

I mean, it might be, though

... you put a-

Right? Like-

... give it a JSON field, say, say confidence, and maybe it spits out something.

Yeah.

You know, and we have done a few evals podcasts over the, over the years, and we did one with Clementine of Hugging Face-

Yeah, yeah, yeah

... who implements the open source leaderboard. And this was one of her top requests, which is some kind of hallucination/lack-of-confidence calibration thing.

And so, hey, this is one of them. And I mean, like anything that we do, it's not a perfect metric or the whole story of everything that you think about as hallucination.

Mm-hmm.

Um, but yeah, it's pretty useful and has some interesting results. Like, one of the things that we saw in the hallucination rate is that Anthropic's Claude models at the, the, the very left-hand side here were the lowest hallucination rates out of the models that we've evaluated omniscience on.

That is a Interesting fact. I think it probably correlates with a lot of the previously not really measured vibes stuff that people like about some of the Claude models.

Is the data set public or what's... Is it-- Is there a held-out set?

There's a held-out set for this one.

Okay.

Um, so it, it-- we, we have published a public test set-

Mm.

-but we, we've only published 10% of it. The reason is that for this one here specifically, it would be very, very easy to, um, like, have data contamination-

Yeah

... because it is just factual knowledge questions. Um, we will update it over time to also, um, prevent that, but we've, yeah, kept most of it held out so that we can keep it reliable for a long time.

It leads us to a bunch of really cool things, including breakdown quite granularly by topic, and so we've got some of that disclosed on the website publicly right now, and there's lots more coming in terms of our ability to break out very specific topics.

Yeah. I would be interested. Let's, let's dwell a little bit on this hallucination one. I noticed that Haiku hallucin- hallucinates less than Sonnet hallucinates less than Opus. And-

Yeah

... would that be the other way around in a normal capability environment? I don't know. What's-- What do you make of that?

One interesting aspect is that we've found that there's not really a, well, not a strong correlation between intelligence and hallucination rate. That's to say that the smarter the, the models are in a general sense isn't correlated with their ability to, when they don't know something, say that they don't know.

Mm.

It's interesting that Gemini 3 Pro Preview was a big leap over here, Gemini 2.5 Flash and, and, and 2.5 Pro. But, and if I add Pro quickly here.

I bet Pro's really good. Uh, actually no.

It's similar.

So I meant, I meant, uh, the GPT Pros.

Oh, yeah.

'Cause GPT Pros are rumored, we don't know for a fact, that it's, like, eight runs and then with the LM judge on top.

Yeah. So we saw a big jump in, this is accuracy, so this is just percent that they get, uh, correct. And Gemini 3 Pro knew a lot more than the other models, and so big jump in accuracy, but relatively no change between the Google Gemini models between releases.

In the hallucination rate.

Exactly.

Gotcha. Yeah.

And so it's likely due to just kind of different post-training recipe between the, the Claude models-

Yeah

... um, that's-

Yeah

... that's driven this.

Yeah. You can, uh, you can, you can partially blame us in how we define intelligence, having until now not defined hallucination as, uh, negative in the way that we think about intelligence, and so that's what we're changing.

Uh, I know many smart people who are confidently incorrect. Look-

Look, that, that, that is-

Very human

... is very true.

Yeah. And there's times and a place for that. I think our view is that hallucination rate makes sense in this context where it's around knowledge, but in many, uh, cases, people want the models to hallucinate, to have a go.

Often that's the case in coding or when you're trying to generate newer ideas. One eval that we added to Artificial Analysis is, is, is Critical Point, and it's really hard, uh, physics problems.

Okay.

And-

Is, is it sort of like a human eval type or something different? Or like a frontier math type?

It's not dissimilar to frontier, frontier math. So these are kind of research questions that kind of academics in the physics, physics world would be able to answer, but models really struggle to answer. So the top score here is n- nine percent.

And when the people that, that created this, like Min Hui and, and, and actually O- Ofir, who was kind of behind Swavand-

What organization is this? Oh, is this, it's Princeton?

Kind of range of academics from-

Okay

... from, uh, different academic institutions. Really smart people. They talked about how they turn the models up in terms of the temperature, as high a temperature as they can when they're trying to explore kind of new ideas in physics as a, as a thought partner, just because they, they want the models to hallucinate.

Mm-hmm. Mm-hmm. Yeah, sometimes it's a feature.

And maybe get to something new.

Yeah.

Yeah, exactly.

It's a feature.

Um, so not right in every situation, but, um, think it makes sense, you know, to test hallucination when scenarios-

Yeah

... where it makes sense.

Well, so the obvious question is, uh, this is one of many that there is, there, every lab has a system card that shows some kind of hallucination number, and you've chosen to not, uh, endorse that, and you've made your own, and I think that's a, that's a choice.

Um-

Totally

... in, in some sense, the rest of Artificial Analysis is public benchmarks that other people can independently rerun. You provide it as a service. Here you have to fight the, "Well, who are we to, to, like, do this?"

And-

Yeah

... your, your answer is that we have a lot of customers and, you know. But, like, I guess, how do you converge the industry on one number that actually everyone agrees is, is the rate, right? 'Cause you have your numbers.

They have their numbers. Never the, the two shall meet.

I mean, I think, I think for hallucinations specifically, there are a bunch of different things that you might care about reasonably and that you'd measure quite differently. Like, we've called this AA Amnesia and Hallucination rate, not trying to declare that, like, it's the only-

Humanity is less than the hallucination.

You could, uh, you could have some interesting naming conventions on all this stuff. Um, the biggest picture answer to that, and something that I actually wanted to mention just as George was explaining Critical Point as well, is, so as we go forward, we are building evals internally.

We're partnering with academia and partnering with AI companies to build great evals. We have pretty strong views on, in various ways for different parts of the AI stack, where there are things that are not being measured well or things that developers care about that should be measured more and better, and we intend to be doing that.

We're not obsessed necessarily with that everything we do we have to do entirely within our own team. Critical Point is a cool example of where we were a launch partner for it, working with academia. We've got some partnerships coming up with a couple of leading companies.

Those ones obviously we have to be careful with on some of the independent stuff. But with the right disclosure, like, we're completely comfortable with that. A lot of the labs have released great data sets in the past that we've used to great success independently.

And so it's between all of those techniques we're gonna be releasing more stuff in the future.

Cool. Let's cover the, the last couple, and then we'll-- I wanna talk about your trends analysis stuff, you know?

Totally. Before that, actually, I have one, like, little factoid on-

Okay

... amnesience. If you go back up to accuracy on amnesience, an interesting thing about this Accuracy metric is that it tracks more closely than anything else that we measure the total parameter count of models.

Ooh.

Makes a lot of sense intuitively, right? Because this is a knowledge eval. This is the pure knowledge metric. We're not looking at the index and the hallucination rate stuff that we think is much more about how the models are trained.

This is just what facts did they recall, and yeah, it tracks parameter count extremely closely.

Okay. What's the rumored size of GPT-3 Pro? And to be clear, not confirmed from any official source.

Yeah, no, not, not at all.

Just, just rumors. But rumors do fly around.

Rumors do.

I get, I hear all sorts of numbers, and I don't know what to trust.

So if you, if, if you draw the line on Omnisia's accuracy versus total parameters, we've got all the Open Weights models. You can squint and see that likely the leading frontier models right now are quite a lot bigger than the one trillion parameters that the Open Weights models cap out at and the ones that we're looking at here.

There's an interesting extra, um, data point that Elon Musk revealed recently about xAI that Grok 3 and-

Four

... four, three trillion parameters for Grok 3 and 4, six trillion for Grok 5. Um, but that's not out yet. Take those together, have a look. You might reasonably form a view-

Yeah

... that there's a pretty good chance that Gemini 3 Pro is bigger than that, that it could be in the five to 10 trillion parameter range. To be clear, I have absolutely no idea. But just based on this chart-

Yeah

... like that's where you would, you would land if you have a look at it.

Yeah. A- and to some extent, I actually kind of discourage people from guessing too much because-

Yeah

... what does it really matter? Like, as long as they can serve it as a sustainable cost, that's about it. Like-

Yeah, totally.

They've also got different incentives in play compared to like Open Weights models who are thinking to supporting others in self-deployment. For the labs who are doing inference at scale, it's, I think, less about total parameters in many cases when thinking about inference costs and, and more around number of active parameters.

And so there's a bit of an incentive-

True

... towards larger, sparser models.

Agreed. Understood.

Yeah.

Great.

I mean, obviously if you're a developer or company using these things, none of it... E- exactly as you say, it doesn't matter. You should be looking at all the different ways that we measure intelligence. You should be looking at our cost to run index number and the different ways of thinking about token efficiency and cost efficiency based on the list prices, 'cause that's all that matters.

It's not as good for the content creator rumor mill, where I can say, "Oh, GPT-4 is this small circle. Look at GPT-5, this big circle." And that, that, that used to be a thing for a while. Um-

Yeah. I mean, but that, that, that is like a, on, on its own actually a very interesting one, right? That-

Is it?

Well, no, j- just purely that chances are the last couple years haven't seen a dramatic scaling up in the total size of these models.

Yeah. Yeah, we hit a wall.

And so there's a lot of room to go up probably in total size of the models, especially with the upcoming hardware generations.

Yes. So, um, you know, taking off my shitposting phase for a minute. Uh, yes, yes. At the same time, I, I do feel like, you know, especially coming back from NeurIPS, people do feel like Ilya is probably right that the paradigm is, doesn't have many more orders of magnitude to scale out more, and therefore-

Mm-hmm

... we need to start exploring at least a different path. GDPVal, I think it's like only like a month or so old. Um, I was also very positive when it first came out. I actually talked to Tejo, uh, who was the, the lead researcher on that.

Oh, cool.

And, uh, you have your own version.

It's a fantastic data set.

Yeah.

And, uh-

Maybe I'll recap for people who are still out of it. It's like 44 tasks that based on some kind of GDP cutoff that is like re- meant to represent broad white collar work that is not just coding.

Yeah.

Yeah.

Each of the tasks have a whole bunch of detailed instructions, some input files for a lot of them. It's, I would, within the 44, it's divided into like 222 to five maybe, um, subtasks that are the, the level of that we run through the agentic harness.

And yeah, they're really interesting. I will say that it doesn't necessarily capture like all the stuff that people do at work. No eval is perfect. There's always gonna be more things to look at, largely because in order to make the tasks well enough to find that you can run them, they need to only have a handful of input files and very specific instructions for that task.

And so I think the easiest way to think about them are that they're like quite hard take-home exam tasks that you might do in an interview process.

Yeah, for listeners, it is not, no longer like a long prompt. It is like, well, here's a ZIP file with like a spreadsheet or a PowerPoint deck or a PDF-

Yeah

... and go, go nuts and answer this question. Yeah.

OpenAI released a great data set, and they released a good paper which looks at performance across the different, you know, web chatbots on the data set. It's a great paper. Encourage people to read it. What we've done is taken that data set and turned it into an eval that can be run on any model.

So we created a reference agentic harness that can run the models on the data set, and then we developed evaluator approach to compare outputs. That's kind of A- A- AI enabled, so it uses, uh, Gemini 3 Pro preview to compare results, which we tested pretty comprehensively to ensure that it's aligned to, to human, human preferences.

One data point there is that, um, even as the, as, as an evaluator, Gemini 3 Pro interestingly, uh, doesn't do, uh, actually that well in GDPVal, uh, AA.

Yeah. The, the thing that you have to watch out for with LLM Judge is self-preference, that models usually prefer their own output. Uh, and in this case, it was not.

Totally. I think the, the, the way that we're, that we're thinking about the places where it makes sense to use an LLM-as-judge approach now are like quite different to some of the early LLM-as-judge stuff a couple of years ago.

Okay.

'Cause some of that, and MTBench was a great project that was a good example of some of this a while ago, was about judging conversations and like a lot of style-type stuff. Here we've got- The task that the grading, grading model is doing is quite different to the task of taking the test.

When you're taking the test, you've got all of the agentic tools, you're working with the code interpreter on web search, the file system, to go through many, many turns to try to create the documents. Then on the other side when we're grading it, we're running it through a pipeline to extract visual and text versions of the files and be able to provide that to Gemini, and we're providing the criteria for the task and getting it to pick which one more effectively meets the criteria of the task out of two potential outcomes.

It turns out that we proved that it's just very, very good at getting that right, matched with human preference a lot of the time because it's, I think it's got the raw intelligence, but it's combined with the correct representation of the outputs, the fact that the outputs were created with an agentic task that is quite different to the way the grading model works, and we're comparing it against criteria, not just kind of zero shot trying to ask the model to pick which one is better.

Got it. Why is this an ELO and not a percentage like GDP Val?

So the outputs look like documents, and there's video outputs or audio outputs from some of the tasks. And so there's-

It has to make a video?

Yeah.

For some of the tasks, yeah.

Some of the tasks.

What task is that?

I mean, it's in, it's in the data set.

Maybe a YouTuber or like-

It's a marketing video.

Oh, wow. What?

Like, model has to go find clips on the internet and try to put it together. The models are not that good at doing that one for now, to be clear. It's pretty, it's pretty hard to do that with a code interpreter.

Um, and the computer stuff doesn't work quite well enough and so on and so on. But, um, yeah.

And so there's no kind of ground truth necessarily to compare against to work out percentage correct. It's ha- hard to come up with correct or in-in-incorrect there. And so it's on a relative basis, and so we use an E-ELO approach to compare outputs from, uh, each of the models, um, between, between the task.

You know what you should do? You should, you should pay a contractor human to do the same task and then give it an ELO. And then so you have-

Yeah

... you have human there. So it's, I think what's helpful about GDP Val, the OpenAI one, is that 50% is meant to be normal human-

Yes

... and, and, and maybe domain expert is higher than that. But 50% was the, the bar for, like, well, if you've crossed 50, you are superhuman.

Yeah. So we, like, haven't grounded this score in that exactly. I agree that it can be helpful, but we wanted to generalize this to a very large number of models. That's one of the reasons that presenting a ELO is quite helpful and allows us to add models, and it'll stay relevant for quite a long time.

I also think it, it, it can be tricky looking at these exact tasks compared to the human performance, 'cause the way that you would go about it as a human is quite different to how the models would go about it.

Yeah. Uh, I also like that you included Llama 4 Maverick in there. Is that, like, just one last, like ...

Well, no. No, no, no, no, no. It is the, it is the best model released by Meta. And so it makes it into the homepage default set still for now.

Other inclusion that's quite interesting is we also ran it across the latest versions of the web chatbot.

Yeah.

And so we have-

Oh, that's right. Oh, sorry, I, yeah, I completely missed that. Okay.

No, not at all. So the, that which has a checkered pattern-

So, so that is their harness not yours, is what you're saying?

Exactly. And what's really interesting is that if you compare, for instance, Claude 4.5 Opus using the Claude web chatbot, it performs worse than the model in our agentic harness.

Mm-hmm.

And so in every case, the model performs, uh, better in our a- agentic harness than its web chatbot counterpart, the harness that they created.

Well, my backwards explanation for that would be that, well, it's meant for consumer use cases, and here-

Totally

... you're pushing it for something-

The constraints are different-

Yeah

... and the amount of freedom that you can give the model is different.

So-

Also, you, like, have a cost goal. We-

Yeah.

Yeah, let the models work as long as they want, basically. Yeah.

Do you copy paste manually into the chatbot?

Yeah.

Yeah.

That's amazing.

That was how we got the chatbot reference once, yeah.

Yeah.

We, we're not gonna be keeping those updated at, like, quite the same scale as-

Yeah.

... running it on the hundreds of models on the harness.

Well, so, and, I don't know, talk to BrowserBase. They'll, they'll automate it for you. You know, like-

True.

Yeah.

Yeah.

We should.

Uh, yeah, I, I have thought about like, well, we should turn these chatbot versions into an API because they are legitimately different agents in themselves.

Yes.

Right?

Yeah.

So-

And that's grown a huge amount over the last year, right?

Mm-hmm.

Like, the tools that are available have actually diverged, in my opinion, a fair bit across the major chatbot apps, and the amount of data sources that you can connect them to have gone up a lot, meaning that your experience and the way you're using the model is-

Yeah

... more different than ever.

What tools and what data connections come to mind when you say what's interesting? What, what, what, what's notable work that people have done?

Oh, okay. So my favorite example on this is that until very recently, I would argue that it was basically impossible to get an LLM to draft an email for me-

Mm

... in any useful way.

Mm.

Because most times that you're sending an email, you're not just writing something for the sake of writing it. Chances are context required is a whole bunch of historical emails. Maybe it's notes that you've made, maybe it's meeting notes, maybe it's, um, pulling something from your, um, any of like wherever you at work store stuff.

So for me, like Google Drive, OneDrive, um, in our Supabase databases if we need to do some analysis on some data or something. Preferably, model can be plugged into all of those things and can go do some useful work based on it.

The things that, like, I find most impressive currently that I am somewhat surprised work really well in late 2025 are that I can have models use Supabase MCP to-

Query

... read-only of course-

Yeah

... run a whole bunch of SQL queries to do pretty significant data analysis and make charts and stuff, and can read my Gmail and my Notion.

And okay, you actually use that. That's good. That's, that's, that's good. Is, is that a cloud thing?

To various degrees supported on both ChatGPT and Claude-

Yeah

... right now. I would say that the stuff like barely works in fairness right now.

Okay.

Um, like-

'Cause people are actually gonna try this after they hear it.

If you get an email from Micah, odds are it wasn't written by a chatbot.

No.

So yeah, I, I think it is true that I have never actually sent anyone an email drafted by a chatbot yet. Um, and so —

But you can, you can feel it, right? And-

Yeah. Yeah

... this time, this time next year we'll come back and see where it's going.

Totally.

Um, Supabase shout-out, another famous Kiwi. Uh-

Yeah

... I don't know if you've, you've any conversations with him about any- anything in particular on, on AI building and AI infra.

We have had, uh-

Yeah

... Twitter DMs, um, with, with him because we're quite big, uh, Supabase users and, and power users, and we probably do some things more manually than we should in, in Supabase across the team.

And so he's just the support line because you're, you're Kiwis.

A, a little bit, yeah. Be- being, being super friendly. One extra, um, point regarding, um, GDP Val AA is that on the basis of the over-performance of the models compared to the, the chatbots, turns out we realized that, oh, like, our reference harness that we built actually wo- works quite well on, like, gen- generalist agentic tasks.

Mm-hmm.

This proves it in a sense.

Mm-hmm.

And so the agent harness is very minimalist. I think it follows some of the ideas that are in Claude Code, and we, all that we give it is context management capabilities, a web search, web browsing, uh, tool, uh, code execution, uh, environment.

Anything else?

I mean, we can equip it with more tools, but, like, by default, yeah, it's, that's it. We, we, we give it, for a GDP Val tool, to, uh, view an image specifically-

Mm-hmm

... um, because the models, you know, can just use a terminal to pull stuff in text form into context. But to pull visual stuff into context, we had to give them a custom tool.

Yeah.

Yeah.

Um, but yeah, exactly. Um-

Yeah

... you, you can de- explain the next bit.

No, so it's, it, it, w- it turned out that we created a good generalist agentic harness, and so we, um, released that on, on GitHub yesterday. It's called Stirrup, so if people want to check it out. And-

Damn

... and it's a great, um, you know, base for, you know, generalist, uh, building a generalist agent-

It is kind of cool

... for, for more specific tasks.

I'd say the best way to use it is Git clone and then have your favorite coding agent make changes to it to do whatever you want because it's not that many lines of code, and the coding agents can work with it super well.

Well, that's nice for the, the community to explore and share and hack on it. I think maybe in, in, in other similar environments, the Terminal Bench guys have done, uh, started Harbor.

Yeah.

Uh, and so it's, it, it's a, it's a bundle of, well, we need our minimal harness, which for them is Terminus.

Yep.

And we also need the RL environment or Docker deployment thing to, to run independently. So I, I don't know if you've looked into Harbor at all. Is that, is that like a, a standard that people want to adopt?

Yeah. We've looked at it from a evals, um, perspective, and we love Terminal Bench and, and host benchmarks of, of, of Terminal Bench on, on artificial analysis. Um, we've looked at it from a, from a coding agent, um, perspective.

Mm-hmm.

But could see it being a great, um, basis for, uh, any kind of agents. I think where we're getting to is that these models have gotten smart enough, they've gotten better, better at tools, that they can perform better when just given a minimalist set of tools and, and let them run, let the model control the, the agentic workflow rather than using another framework that's a bit more built out that tries to dictate the, dictate the flow.

Awesome. Let's cover the openness index, and then let's go into the report stuff. Uh, so that's the, that's the last of the proprietary, uh, numbers I guess. I don't know how you sort of classify all these.

Yeah. Or call, call it, let's call it the last of, like, the, the three new things that we're talking about-

The three new things

... from, like, the last few weeks.

Yes.

Um, 'cause there, I mean, there's a-- We do a mix of stuff that, where we're using open source, where we open source some of what we do, and, um, proprietary stuff that we don't always open source. Like long-context reasoning data set last year we did open source.

Um, and then all of the work on performance benchmarks across the site, some of them we're looking to open source, but some of them, like, we're constantly iterating on and so on and so on and so on.

Yes.

So there, there's a huge mix, I would say, just of, like, stuff that is open source and not across the site.

So that's AALCR for people-

Yeah. Yeah, yeah, yeah

... who don't know. Uh, but let's talk, let's, let's talk about open.

Let's talk about openness index. This here is, call it like a new way to think about how open models are. We for a long time have tracked where the models are open weights and what the licenses on them are, and that's, like, pretty useful.

That tells you what you're allowed to do with the weights of a model. But there is this whole other dimension to how open models are that is pretty important that we haven't tracked until now, and that's how much is disclosed about how it was made.

So transparency about data, pre-training data and post-training data, and whether you're allowed to use that data.

Mm-hmm.

And transparency about methodology and training code.

Mm-hmm.

So basically, those are the components. We bring them together to score an openness index for models so that you can, in one place, get this full picture of how open different models are.

I feel like I've seen a couple other people try to do this, but it, uh, they're not maintained. I, I do think this does matter. I don't know what the numbers mean apart from... Is there a max number?

Is this out of 20?

It's out of 18 currently.

Oh, 18. Okay.

And so we've got an openness index, um, page. But essentially, these are points. You get points for being more open across these different categories, and the, the maximum you can achieve is 18. So AI2 with their extremely open Olmo3 32B Think model is-

It's Hugging Face

... the leader in a sense.

It's Hugging Face.

Oh, with their, with their smaller model?

Yeah.

Um, it's coming soon. I think we need to run, we need to get the intelligence benchmarks run-

Yeah. My team

... to get it on the site.

You can't have an openness index and not include Hugging Face. Like it's-

We love Hugging Face. We'll have that, we'll have that up very soon.

It's mean, uh, you know, they're Refined Web and all, all that stuff. It's, uh, it's amazing. Or is it called Fine Web? Fine Web.

Fine Web. Yeah, yeah, yeah. No, totally.

Yeah.

Yep. One of the reasons this is cool, right, is that- If you're trying to understand the holistic picture of the models and what you can do with all the stuff the company's contributing, this gives you that picture. And so we are gonna keep it up to date alongside all the models that we do intelligence index on on the site, and it's just an extra view to understand.

Can you scroll down to the, the, the trade-offs chart? The, the... Yeah. Yeah, that one.

Oh.

Yeah, this, this really matters, right?

Yeah.

Obviously.

Yeah.

'Cause you can be super open, but dumb.

I mean-

And

... the slide obviously goes the wrong way here, right? Um, and-

A lot of people would like to see, uh, labs hill climb on the end target.

This is the-

The, uh, openness index.

Yeah, yeah, yeah. This is the access to, to hill climb, yeah.

Unfortunately, it might be fundamentally true that the, the slump will always go this direction because-

Uh, okay

... once you open something up, then everyone else can get to the level of what you have done.

Well, so let me, let me tweak your point system, right? Like, you have these, like, numbers on the point system, and they go up to 18, you know, but, like, just because I have a little bit of open data doesn't mean I'm necessarily that much better as, in someone who put a lot of effort into their open weights that is, that is smarter.

Yeah.

So I might, I might just mess with the point system to make sure that, like, I'm accurately representing the, the contribution to the open sys- openness.

It is hard to wait for the materiality of the contribution to, to open source. Like with it, it's... We, we, we tried to make it so that it is quite well-defined, and no one can disagree about, like, which, um, category things should be in.

So we're not saying, like, this was a big contribution or a small contribution in terms of, um, impact on the industry or anything. It's just, like, how much of your data did you release? I would say that it is still valid to say that we trained a model that's not that smart, maybe even not at the frontier for a particular size category, but we chose to open up all the data, all the training code.

That is a very useful exercise for the industry, and we want to recognize that even if the smartest model in the category.

Yeah. Yeah, a-and also a special shout-out to NVIDIA NeMo Tron, which doesn't get enough credit for the amount of stuff that they do.

Yeah.

And honestly, it's, uh, it's sales enablement for NVIDIA as well. Like, the fact that they can do this as a side project.

Totally. But I mean, but it, it is true that NVIDIA have actually put an enormous amount of effort over the last year especially into the NeMo Tron models.

Yeah.

And it really paid off.

And so many people even use it for, like, synthetic data and stuff. Like, it's, it's, uh, it's a pretty interesting secret of the industry that, uh, NVIDIA holds up all these guys.

I mean, it's, it's in their interest for there to be more AI, right?

Uh, so obviously I think you want to push openness as, as having an index. E-every index that you push, like, has encoded some kind of opinion or value.

Yes.

I think one of the openness questions o- from this year was people messing with the in, the, the license. And so-

Yeah

... Llama had this, like, if you have 700 million daily active users, you're not allowed to use our model, or you have to talk to us, something like that. So basically, like, what are your customers telling you about the kind of licensing worries that they have, right?

Because obviously most people will never hit 700 million users.

We have, like, a detailed breakdown of that in the Openness Index, and that was actually one of the initial questions, like, took us down the route of wanting to do this. Um, 'cause yeah, the simplest thing that, like, our opinion is is that there is a lot of advantage to having, like, a official OSI license like MIT or Apache 2.0 because then the box is just checked.

Checked.

You don't even need to read it because it's just Apache 2.0, and you can do whatever you want, and it's fine. There are often very good reasons that companies don't want to release language models with those completely open licenses.

The index tells you. So if you-

Cool

... get the top category, that's one of those licenses, you're totally good. And then we've got, um, some lower categories for when attribution is required, um, and then when commercial use is not allowed. Yeah, they're there.

So that's the Openness, Openness Index. Thank you for doing all those, all those works. Let's talk a little bit or at least end the pod on just the, the trend reports that you guys do, which is kind of a bit of the bread and butter, how you make money.

Highly encourage everyone to see George's talk at World's Fair, which gives a little bit of a preview, and you're, you were very excited about talking about the smiling curve, or I don't know what you call it. Um-

Yeah. Yeah, yeah, yeah. Yeah, let's talk about that one.

Let's explain it for people and, and I might, I might actually put, put it up, um, because I don't have it in front of me.

Yeah.

Oh, great. Yeah. That'd be cheap.

Got a, got a copy of the slide. That'd be-

That's cheap

... that'd be excellent. Um-

It, it's, it's important for people to have in their head because yeah, people only get the marketing message from the labs that, "Oh, we're cutting costs all the time."

Yep. Yep. But it's, it's true. Just that it's not the whole picture. So okay, a couple of, like, the big trends that we track at Artificial Analysis over time and that, like, we're always showing charts of on the trends page in these reports and stuff.

One, that the cost of intelligence has been falling dramatically over the last couple of years. The best way to think about that is that the cost for each tera of intelligence-

Each tera, yeah

... has been dropping. The, like, one fact on that is that you can get intelligence at the level of GPT-4 for over 100 times cheaper than GPT-4 was at launch right now.

I think my number's 1,000 actually. If you look at, um, the Amazon Nova models, which are very, very cheap.

Yeah. Like, uh, my, my conservative, uh, statement is normally, like, 100 index.

100 is conservative.

But in fairness, this slide, like, I-- we were actually saying before the podcast, right, it's, like, maybe six months old now, and it's conceptually still correct but, like, could actually probably do with a tweak-

Yeah, it should be around

... on the exact numbers because, like, the market's moving so quickly.

Yeah, feel free to kick it off. I, I, I mean, w-we'll have this chart. I told people to watch the World's Fair talk. But let's, let's introduce what context makes you make something like this.

There are two trends that seem to not make sense together, both of which we talk a lot about at Artificial Analysis and are very important to developers building stuff in AI. The first is that the cost of intelligence for each level of intelligence has been dropping dramatically over the last couple of years.

We track the cost to run Artificial Analysis Intelligence Index for each bucket of intelligence index scores, and each bucket you just see the line go down really, really quickly and actually go down more quickly to each new level of intelligence that's been achieved over the last couple of years.

So the rate of that cost decline has actually been going up. So we've got that being true. And yet it is clearly possible to spend quite a lot more on AI inference now than it was a couple of years ago.

Nvidia stock go up.

It's going, it's going really up. Uh, I just heard from a friend's startup that just went through the Shift Zero. They're spending $5,000 per employee on coding agents spend alone.

That's, uh-

That's a ridiculous amount of coding

... that's an impressive number. We need to get our numbers up. We're, uh, we're not, we're not quite- ... hitting, hitting quite that high.

Well, it's so high that I'm like, "Are you doing something wrong?" Yeah.

It's 'cause there are some efficiency questions along the way. But, like, you can make AI inference useful to that level in a bunch of ways that I can imagine, right?

Yeah.

Um, I, I don't think that's that nuts. Um, but basically the re- the reason we made this slide to ask the question, right, is to show that the crazy thing is that it is actually true. We've had this 100x to 1000x decline in the cost of GPT-4 level intelligence on the left-hand side, and yet on the right-hand side, because the multipliers are so big for the fact that even though small models can do GPT-4 level now, we still want to use big models and probably bigger than ever models to, um, do frontier-level intelligence.

We've got reasoning models using tokens, and then we're throwing them in these, them in these agentic workflows where they're consuming enormous numbers of input tokens and making enormous numbers of output tokens, working for a really long time. Those two things taken together get you back to we can spend enormously more today than we could a couple of years ago.

Yep, I think that's right. There's a number of drivers at play, and we kind of outline kind of six key ones here. Um, but, you know, as complex, it's changing quickly. All of these have changed very dramatically in the last, uh, in the last 12 months.

Le-let's pick on hardware efficiency since-

Mm

... you also have, you also track hardware stuff. And I think the general assertion or the, the message is that the efficiency from next gen Nvidia chips is actually not 4X or you have what 3X or 4X. You have 3X in here, and it's, it's like 2X maybe or it's more of like a power story rather than like a, a sheer sort of compute tokens efficiency story.

But yeah. What, what's going on in, in hardware?

Okay. So the, the, the, the answer unfortunately, uh, is it depends, and it just depends massively on like so many things across a bunch of different types of workloads and ways to think about it. So one of the simplest ways to think about this is to take single relevant model, to think about serving it at speeds that are realistic for what you actually might want to hit and can afford to hit, and then think about the throughput per GPU that you can achieve serving the model at those speeds.

Reason-- One of the reasons that's important is that there's a trade-off between the throughput per GPU that you can achieve and the per user speed that you can achieve. And as in it costs more to serve stuff fast to users.

When you run all of that for especially big sparse models, you can get a lot better than 2 or 3X gain going from Hopper to Blackwell generation Nvidia. I am... This shouldn't be too controversial a statement, but like I'm pretty confident that Blackwell has delivered pretty enormous gains and that the next couple of years of Nvidia's roadmap are going to continue to deliver quite enormous gains and that those will actually come through as lower total cost per token to the companies that are running models on them and will allow bigger models, will allow way more tokens to be made for lower cost, and that that's gonna continue.

These things also stack on all of the software and model improvements being made. So basically, like my prediction across like both sides of that like smile chart, uh, that we're gonna see the left-hand side continue to be true.

And probably like for another order of magnitude and the right-hand side continue to be true for another order of magnitude. And that's gonna enable a whole lot of things.

Okay. Well, I'll push on... Let's go back to the, the, the smile chart. I'll push back on sparsity, right? W- uh, we've gone a long way on sparsity. DeepSeek was a major pusher of fine-grain experts, let's call it.

Yep.

Right? Well, I'm, I have a mental number of sparsity in terms of, let's say, active params versus total params.

Yep.

And that number went from 25%-

Yep

... let's say, down to like 15, right? You obviously can't really go below, I don't know, five.

Is that obvious?

So, so there's a lower limit to, to sparsity is what I'm saying.

I don't know that that's that obvious actually.

All right.

Um, there, there must be a lot somewhere, right?

Yeah, exactly.

But we've got numbers in the wild that are quite a lot lower than that right now. So the GPD OSS models, like the big ones at about 5%, um, active. Chemike-2 is at like 3% active.

Three? Oh, ooh. Okay.

I think. Pretty sure.

I, I've looked at those numbers. I've calculated them. I don't remember. Yeah. But I, I remember thinking like-

Yeah

... this must be it.

Y-y-your 5% is- ... i-i-yeah, is exactly, is like around the ballpark for the- ... for the open weights models of, of what's released today. I think one interesting that gives me kind of pause when thinking that it won't go, the sparsity won't go higher or the number of percentage of active parameters lower, is that we in our benchmark see a lot of performance to- correlated more with, uh, total parameters than active and not that correlated with how sparse like the models are.

Our accuracy benchmark as part of AA Omniscience, it's very correlated with total. It's not correlated with, with active, uh, parameters.

Yeah.

Which I think is very-- at all, which is very, very interesting. And so I think, yeah, there could, there could be quite a bit, um, to go here.

Awesome. Well, we don't have that much time, but I w- I did want to leave some room to cover reasoning and non-reasoning models and token efficiency.

Let's do that one.

So at a, at a super high level, people have to classify this binary thing of reasoning versus non-reasoning. People who are insider have some discomfort with that because basically-

Totally

... you just have the think tag or no think tag. How have you guys decided to approach this, and also how does that s- laid out in over, over the course of the year where we have things like GPT-5, which is a model router?

Let's say GPT-5 and ChatGPT, the consumer experience is a model router. When you're hitting the API, like we can... you can pick the different versions, and you can pick reasoning strength of the different versions. But that, that goes to why this is now such a complex thing.

So earlier this year, and probably when you and George last spoke for the AI Engineers World's Fair, we had this great slide that was super easy where we would show that the average reasoning model is using 10 times the number of tokens per query in our intelligence index as the average non-reasoning model.

And there was this moment where that was a pretty clear distinction and extremely useful to look at it just like that. Definitely no longer the case, not least because you can think about reasoning strength for a bunch of these different models, but particularly because different models have wildly different token efficiency now, more than an order of magnitude in difference.

That means that the way that you probably need to think about cost for any application is to use something like our cost to run intelligence index metric as the starting point for what it's going to look like for these different models, these different reasoning strengths, and this continuous spectrum from non-reasoning to reasoning.

That's basically like where we're at. So we will still show reasoning and non-reasoning and define reasoning as when there is that separated chain of thought that you're getting at a different parameter in an API normally. But it doesn't necessarily anymore mean that that model is actually going to have longer end-to-end latency, that it's going to use more tokens than something that is branded a non-reasoning model for the same task.

Mm, that's true. I think 5.1 was it, and then, uh, 5.1 Codex had these, these chart which was super nice of this like, let's say, bottom 10 percentile query being faster but l- top 10 percentile being longer, and that's a kind of the efficiency chart you want to see, right?

Yep. That, so, so that is a, an extra thing. Let's say, let's say, let's say that we've got... That, that's a really important extra thing though, right? That you've got not just the average number of tokens being used by the model, which we cover really well right now, but the b-behavior that you want in the model is it to use more tokens when it needs more tokens and not to use more tokens when it doesn't need more tokens.

So that's what OpenAI were basically claiming that 5.1 Codex is better at. We don't actually publish anything on this right now, but have tracked it a bunch internally in our internal analytics on evals across all the models that we run, where we look at the difficulty of the questions and the correlation between token usage and difficulty, and net-net, surprise, surprise, like models have got better at doing that over the course of this year.

I think going into next year, that's gonna be really important, especially as you multiply it by the number of steps in an agentic workflow that a model has to take to get to an answer. We are going to care a lot about token efficiency and number of turns efficiency for getting to what we want.

Which would you rather have, token efficiency or number of turns efficiency?

Um-

Or like which is more important to work on?

It's like it depends on the application, and both are gonna be really important.

Ugh. Yeah.

'Cause your total, your total cost is just-

Like Taubich retail, Taubich airline.

Yeah. I- interestingly, in Tau, um, Tau2Bench Telecom, it's cheaper to run m- you know, on a per token basis more expensive models like a GPT-5 compared to some smaller open source models because the, um, some of the GPT-5, for instance, uh, got to the answer faster, and so was able to resolve the customer's query faster in fewer turns.

And maybe it used more tokens per turn, but it certainly cost more per token. So you would always rather use GPT-5 in, in, in that scenario. And so I think that's what, that's where we're getting to. I think number of turns is, is gonna be a metric that we're gonna be talking about a lot more, and, uh, I think it'll be something that people want to, uh, really start to think about, uh-

Yeah

... a lot more.

There's a trade-off in benchmarking here where most benchmarks needs to be one turn to be autonomous, to be parallelized and all that, but most, a lot of your real life use cases need to be multi-turn and especially like quick multi-turns, so you can align.

Yeah.

Yeah. I mean, I, I would say that historically benchmarks have been single turn, but I wouldn't say they need to be at all into the future, right? Like, we have a couple of agentic benchmarks in the index right now and GDP Val that we were talking about.

We let the models do up to 100 turns and, um, our stirrup agent accounts to do that eval, and we're gonna build similar stuff like that in the future. It definitely is hard, and you've got whole kinds of infrastructure problems to run that and exactly as you say, parallelize it, because we need to run that on hundreds of models, and we want to do that really fast when new models come out and when labs want us to run it on their models.

But you can do it. We're putting in the work to build that stuff, and it's gonna be great.

Okay. So we've covered... I mean, there's a lot more to cover, and you haven't even touched on multimodal, which is ... that's also huge.

We also do speech benchmarking-

Speech

... image benchmarking-

Image

... uh, video benchmarking-

Video

... hardware.

I like the way that you've done it, uh, 'cause it's very smart-

Mm

... which is, uh, video takes a long time, so you pre-generate, right? So then people just pick their preferences, and you can see the, the overall arena results, and you also avoid like any sensitivity issues ar-ar-around like, you know, unsafe content that, that is being generated.

Yeah. And you can see it as a, a good, good thing or bad thing depending on what your view is, but it means that we have a quite active creative direction approach to trying to understand what creative professionals and users want to do with those image and video models, and so that we can be directing the arenas in our categories toward gathering votes on what people care about.

One call-out actually to listeners, like if you are using our arenas, is that you can submit requests to us for things that we should cover.

I didn't know that.

And-

Yeah

... understudied categories, areas that you think the models are bad at and the labs don't focus on enough. Like, if you want something solved, one of the levers that you have is send us a couple of prompts on it.

We might be able to get a category going on it, and this thing we were talking about earlier, right, that once things get measured, they can get targeted. You can make that work for you.

For me, as a content creator, infographics.

Mm.

Very needed. I took the latest DeepSeek paper and, uh, I, you know, they had some descriptions of their search agents and their coding agents, and I put it in and I need- I created an infographic. And, um, I, I just think like that's an industrial use case that doesn't require a lot of, I guess, design taste, but just requires some, like you need to conform to some Preset references, which is something that, uh, that is increasingly important, especially in, like, the Nano Banana series.

But, um, yeah, and I think, like, OpenAI is releasing Image 2 soon, which, um, is gonna have that. So I, I, I think, like, it's, it's all, like, of a kind, where people need to incentivize, like, workhorse use cases and not just art.

I don't know.

Totally. Yeah.

And what are we gonna be talking about next year? Like, what's, what's, like, what's emerging that you're seeing and, like, maybe not in the discussion?

The first answer that I'll give to that is the, the boring answer, is that on most of our charts, the lines go in a particular direction, and our overall prediction is the lines are gonna keep going-

Keep going.

... in that direction. We're, we're gonna do a lot, and do a lot to be as useful as possible to developers and companies to measure what's important on every one of those and along those lines, but I think we're gonna talk about similar stuff.

It's just that we're gonna have continued on this trajectory for another year, and things are gonna feel pretty different because of that happening. I know this is the boring answer to that question. Um, so, like-

No, no, I mean, you know, I, I'm a fan of things, uh, that, truths that don't change because you can build and plan for that. And I think in media in general, in the podcast business, newsletter business, Twitter business, people are addicted to change.

Like, "Oh, everything's breaking, everything's..." No, like, there's some truths that are just constants that you can plan on and build and yeah.

Yeah.

I, I think one of the truths is that the demand for AI intelligence and smarter AI intelligence is going to be insatiable. Um, o- and some people disagree, that, okay, once we reach certain thresholds, then you don't need more intelligence.

I think to that I ask people, have they ever worked with or managed someone in a work environment and wouldn't press the button that they were smarter to make them smarter or better at their job, or, or would they never press that for themselves?

And I'm not sure that that's, that's the case.

Yeah.

But I think for Artificial Analysis, we'll keep benchmarking, uh, raw intelligence, but we also wanna think about it and explore models more deeply across other axes as well. I think hallucination's the start of that, but we're getting into wanting to support people and understanding, okay, the behavior, the pers- personalities, uh, of the models to help people make more nuanced, uh, decisions.

You're gonna have a personality bench.

Maybe.

That is a direction that ChatGPT, OpenAI is leaning into a lot. Uh, so if you manage to solve that, you should definitely talk to, uh, Fiji and Rune. Oh, okay, um, yeah, so what is gonna be included in, let's say, like, a V3 of the Intelligence Index?

Because obviously you're gonna saturate i- in March.

Why don't we break it now?

How soon is the podcast- ... gonna come out?

Whenever you want.

Okay. So R- so we're, we're at V3 right now, so the, so the, the version that we, that's going inside is, is, is V3. V4 is what we're gonna call the next, you know, major update, surprise, surprise. We're gonna be adding several of the things that we've actually talked about today that we've launched over the last few weeks.

Got it.

So it's not, that's not gonna be wildly shocking, but some of the things that are most exciting is that adding GDP Val is gonna give us this general agentic performance in a really strong way in Intelligence Index. Adding Critical Point, the, um, physics eval George was talking about, similar to frontier math, that gives us completely new view with a brand-new data set of very, very hard research problems.

We are gonna be using omniscience, and we are gonna be using hallucination rate. The exact ways that all those are gonna come together, um-

The weighting's gonna be hard 'cause the numbers are different.

Yeah.

Yeah.

We g- we, we're gonna make sure that we don't- ... do anything to cause odd distortions and stuff that could be misleading. But-

But each, every time you version it, you have a one-time reset of the-

Exactly

... you know?

Yep.

Yeah.

Yep, that's exactly how we think about it. We will make sure that within each version number that there's no, um, drift in any of the scores so that people can rely on them and reference them.

Yeah.

Um, you just have to watch out for that version number. Once it's V4.1, those numbers won't be compatible with V4.

Of course. Uh, there, there is a little bit of debate over the, the accuracy of Tau bench. I don't know if yous- you're clued in to what's going on. Apparently, like, a, a very high number of Tau, Tau bench tests are impossible.

Potentially for the earlier versions, Tau, Tau bench Telecom-

Yeah

... we're pretty convinced-

Good. Okay

... is pretty good. If anything, the only issue there is that models have got very good at doing it, and so, like anything-

Mm. Tau 3.

Yeah.

Yeah.

On we go.

Yeah, on we go. All right, well, thank you so much for, uh, providing such a great service to the industry. I, I, I'm glad to at least know you guys as before you got famous, and now, now you are famous.

So.

Oh, look, our pleasure, and we really appreciate your support along the way.

Yeah, yeah.

Like, I, I wasn't kidding at the start, right, that it was a, um, quite material moment for us, like, when Artificial Analysis was covered on Latent Space.

Some, some random guy in San Francisco mentions you, and

Well, no, so I, I, I was a fan of Latent Space for, like, a year-

Oh, really? Okay

... before you mentioned us, so-

All right

... I'd been, I'd been, I'd been listening. Um, I don't think I was, um, like, familiar with, um, like, you personally yet at that point, but, like, I was... I listened to your voice probably for many, many hours.

Oh, okay.

And so once, like, you mentioned-

It's nice to hear

... and then, like, got to get to know you and, like, meet you for the first time nearly a couple years ago, like, it was really cool, honestly.

Yeah.

So yeah.

Yeah.

It's great to be here.

And thanks for, you know, being such a great member of the community and kind of spotlighting, you know, projects which aren't, don't have attention and, and bringing them to your, to your audience.

Yeah. Uh, well, actually, so it wasn't me, right? Uh, someone in the Discord dropped it in our, in our Discord, and that's... I, I rely on our community, and it kind of feeds itself, right?

Nice.

So, uh, so someone brought it to my attention. I don't know who. We should probably go back and check. But, uh, once I saw it, I was like, "This is, this looks good. This is something I always wanted."

I, I, I wanted to build it. I, I was too shy or dumb or lazy to build it, and you guys did, and, um, now, now it's a whole thing, so thank you for doing it.

You built some really cool other stuff, like, like this pod. Yeah, yeah.

Totally.

So thank you.

That's it.

Great.

Cool.

Thank you.

Thanks.