Will an LLM report >50% score on ARC in 2025?
Plus
18
Ṁ37342025
82%
chance
1D
1W
1M
ALL
ARC is a general-purpose AI eval designed to test intelligence as opposed to memorization. https://arcprize.org/arc
This market resolves to Yes if there are public demonstrations of general-purpose base models from OpenAI, Anthropic or Deepmind that solve at least 50% of the ARC questions before 2026.
(note that this is separate from winning the arc price, which requires only using open-source models)
This question is managed and resolved by Manifold.
Get
1,000
and3.00
Related questions
Related questions
Will GPT4/Opus report >50% score on ARC in 2024?
37% chance
LLM Hallucination: Will an LLM score >90% on SimpleQA before 2026?
55% chance
Will an LLM be able to solve the Self-Referential Aptitude Test before 2027?
66% chance
Will LLMs mostly overcome the Reversal Curse by the end of 2025?
66% chance
Will an LLM be able to solve the Self-Referential Aptitude Test before 2025?
20% chance
What will be true of Anthropic's best LLM by EOY 2025?
Which company will have the best LLM by the end of 2024?
Will the ARC-AGI grand prize be claimed by an LLM?
43% chance
Will an LLM improve its own ability along some important metric well beyond the best trained LLMs before 2026?
58% chance
Will I think that the top Chatbot Arena scores accurately reflect which LLMs are most capable and useful at EOY 2024?
46% chance