Claude score on Humanity’s Last Exam by June 30?

such an easy yes, it has already passed 50% on artificialanalysis

You must be new here

What is the major case for why this would not be a Yes? Is it the fact that the website has not been updated in a while so it would technically resolve to a No?

They think so.

too far to end of June

Good chance they will not even update the leaderboard anymore in June hahaha

Lol

Fable 5 definitely will.

So the leaderboard has stayed the same, and we're getting closer to June 30. How is the probability that it will exceed 45% increasing then?

Because Mythos might get released/benchmarked

I think Mythos is focused on coding and cybersecurity, so I don’t expect it to be 10%+ stronger specifically on Humanity’s Last Exam.

Stop gambling start predicting girl!

Anthropic officially reports: * Claude Fable 5: 59.0% HLE (64.5% with tools) * Claude Mythos Preview: 56.8% HLE (64.7% with tools) * ✅ Independent evidence already exists: * Artificial Analysis: Fable 5 scored 53.0% HLE, which is still well above 45%. * ❌ Scale’s HLE leaderboard has not been updated yet with the new Claude models

free money?

eu, free ca

eu, free cas

who tf bought Y at 90c when 4.6 can't even hit 35%, and 4.7 slightly better 🤣

RolandChang if you wanna exit I have some exit liquidity on the book for you, price will only keep getting worse as time goes on.. If you want to negotiate full exit you can dm me on X

You're too nice to these people Mr joker man

No, dude should buy more Y, fill my orders

Thanks for the fills retards

My dog has no nose. How does it smell? Awful.

emergency: my dog has GDV and needs immediate attention, can you please spare $10 to help? i am just being desperate.

my dog got GDV and is in emergency surgery, the bill is way over my head, could anyone donate $10? i am just desperate.