Live data from Hacker News

Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard

artificialanalysis.ai

1–10 of 251 posts

Re: Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard

#3

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

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

Re: Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard

#5

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

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

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

Re: Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard

#6

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

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

Probably because they made ASICs to run inference for less.

Re: Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard

#7

Earlier quoted context omitted.

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

Probably because they made ASICs to run inference for less.

Are those actually deployed at scale yet?

Re: Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard

#9

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

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

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

Like 96% vs 93% or something

Re: Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard

#10
post #7

Earlier quoted context omitted.

Are those actually deployed at scale yet?

Yes.

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.
Post reply on HN