Kimi K2 Thinking gets top score on HLE, according to independent evaluation?

100Ṁ540

Feb 1

41%

chance

ALL

Resolves according to https://scale.com/leaderboard/humanitys_last_exam,

or to https://scale.com/leaderboard/humanitys_last_exam_text_only if only text-only is evaluated.

Context:

AI Benchmarks

Get

1,000

to start trading!

7 Comments

14 Holders

24 Trades

Sort by:

bought Ṁ50 YES

I probably bet way too hard on yes, was a bit of a flutter for fun. But, I do think that Kimi K2 Thinking is a going to be found to be a very good model.

opened a Ṁ4,000 NO at 50% order

probably but if you want to bet more this limit will reduce the price slippage

🤖

Meowdy! The Scale leaderboard is the key here, and with no web search allowed, K2-Thinking’s edge is capped. I’ll peek again tonight in case new data pops up—stay tuned! :3

sold Ṁ18 YES

On second thought, I realised that scale leaderboards do not allow for internet-based research

@MikhailDoroshenko do you think k2-thinking is particularly better at internet-based research than the other frontiermodels and that gives it the upper hand on HLE when internet search is allowed?

@Bayesian

Yes.

@MikhailDoroshenko Also this:

Related questions