Grok 4 Heavy gets on Humanity's Last Exam leaderboard?
2
100Ṁ71Sep 2
32%
chance
1H
6H
1D
1W
1M
ALL
The market resolves YES if Grok 4 Heavy has a score in the leaderboard section of https://agi.safe.ai/, regardless of settings (text-only, tools-allowed, etc.).
While the market stays open, it resolves NO when either of the following happen:
The next major iteration of Grok models is released by xAI without Grok 4 Heavy being generally accessible (including eg. limitation to paid users) in the official xAI API. Examples include Grok 4.2, Grok 4.5, Grok 5.
Grok 4 Heavy is made generally accessible in the official xAI API for a month.
In short, YES if Grok 4 Heavy ever appears on the HLE leaderboard; NO if either (i) a newer Grok generation ships first, or (ii) Grok 4 Heavy is on the xAI API for 30 days without reaching the leaderboard.
This question is managed and resolved by Manifold.
Get
1,000 to start trading!
People are also trading
Related questions
What is Grok 4's performance on METR's task length evaluation?
Will OpenAI's o4 get above 50% on humanity's last exam?
26% chance
Will Grok 3.5 Top the Chatbot Leaderboard?
1% chance
Humanity's Last Exam score in 2025?
55.4
Open-source OpenAI model beats Grok 4 on LMArena?
22% chance
What is Grok 4 Heavy's performance on METR's task length evaluation?
Grok 4 in top left of Artificial Analysis' cost to run vs intelligence chart?
4% chance
Top score on Humanity's Last Exam > 80% by what year?
Top score on Humanity's Last Exam > 90% by what year?
Top score on Humanity's Last Exam > 60% by what year?