Will LLMs solve the first 15 days of Advent of Code? | Manifold

Will LLMs solve the first 15 days of Advent of Code?

21

100Ṁ844

Dec 16

7%

chance

1H

6H

1D

1W

1M

ALL

AdventofCode is an annual, daily advent calendar-style series of progressively more difficult coding problems. Using only LLMs, will I be able to solve the first 15 days worth of problems?

The AI must be able to solve both parts of the problem for each of the listed puzzles from December 1st - December 15th, 2024 for this to Resolve YES.

I will not be providing any algorithmic help to the LLM, it needs to come up with the meat of the solution itself. However, if it makes simple mistakes, ones that people who don’t know how to code would catch, I will assist it with those. I will be sharing all successful prompts here, and will not be betting in this market.

Get

1,000

to start trading!

People are also trading

Will an LLM get > 50% on hard problems on LiveCodeBench Pro?

Will there be an Advent of Code 2025?

Will the best public LLM at the end of 2025 solve more than 5 of the first 10 Project Euler problems published in 2026?

Will an AI win Advent of Code? (2025)

Will OpenAI's next major LLM (after GPT-4) solve more than 2 of the first 5 new Project Euler problems?

EOY 2025: Will open LLMs perform at least as well as 50 Elo below closed-source LLMs on coding?

Will an LLM agent complete >50% of the lab tasks on the Factorio Learning Environment benchmark in 2025?

Will LLMs be able to formally verify non-trivial programs by the end of 2025?

Will there be any simple text-based task that most humans can solve, but top LLMs can't? By the end of 2026

When will LLMs be able to generate formal proof for sudoku solver?

Related questions

Will an LLM get > 50% on hard problems on LiveCodeBench Pro?

Will there be an Advent of Code 2025?

Will the best public LLM at the end of 2025 solve more than 5 of the first 10 Project Euler problems published in 2026?

Will an AI win Advent of Code? (2025)

Will OpenAI's next major LLM (after GPT-4) solve more than 2 of the first 5 new Project Euler problems?

EOY 2025: Will open LLMs perform at least as well as 50 Elo below closed-source LLMs on coding?

Will an LLM agent complete >50% of the lab tasks on the Factorio Learning Environment benchmark in 2025?

Will LLMs be able to formally verify non-trivial programs by the end of 2025?

Will there be any simple text-based task that most humans can solve, but top LLMs can't? By the end of 2026

When will LLMs be able to generate formal proof for sudoku solver?

© Manifold Markets, Inc.•Terms•Privacy