Will OpenAI's next-generation model score 65% or higher on the GPQA benchmark?
13
Ṁ1kṀ803resolved Sep 16
Resolved
YES1H
6H
1D
1W
1M
ALL
Resolve to YES if OpenAI's next generation language model scores 65% or higher on the GPQA benchmark(extended set).
If OpenAI's existing model gets 65% or higher by post-training enhancements, that also counts.
There's room for improvement via prompt engineering after the release, but I don't know how long I should wait, so I will resolve this question as soon as OpenAI releases their next model.
This question is managed and resolved by Manifold.
Market context
Get 
1,000 to start trading!
1,000🏅 Top traders
| # | Trader | Total profit |
|---|---|---|
| 1 | Ṁ168 | |
| 2 | Ṁ68 | |
| 3 | Ṁ23 | |
| 4 | Ṁ22 | |
| 5 | Ṁ11 |
People are also trading
Related questions
Open-Source AI model gets perfect IMO 2026 score? [International Math Olympiad 2026]
44% chance
In what year will AI achieve a score of 95% or higher on the GPQA benchmark?
5/25/27
Will the gap between open-weights and frontier models on GPQA Diamond be at most 7%?
6% chance
What will be the best OpenAI-Proof Q&A score by Dec 31, 2026?
Will OpenAI announce a new model that EpochAI estimates is at least as large as GPT-4.5, before August 2026?
43% chance
Will OpenAI's o4 get above 50% on humanity's last exam?
16% chance
Will OpenAI announce a new GPT-5-level model before 1 July 2026?
96% chance