Will the next LLM released by OpenAI be worse than GPT-4 at MMLU?
23
1kṀ1163Jan 1
16%
chance
1D
1W
1M
ALL
The next LLM = the next family of LLM in cases of doubt - an updated version of a previous model doesn't count as a new model for this market
This question is managed and resolved by Manifold.
Get
1,000 to start trading!
1,000Sort by:
Afaik OpenAI has not made a model worse than their previous model before. (gpt-3.5-turbo & text-davinci-003 perform about the same overall so i'm not counting that) and I'm pretty sure ada/babbage/curie/davinci were all released at the same time, and the best of those, davinci, was better than early gpt-3, so that wouldn't count either
Related questions
Related questions
Will OpenAI's next major LLM (after GPT-4) surpass 74% accuracy on the GPQA benchmark?
85% chance
Will OpenAI's next major LLM (after GPT-4) surpass 70% accuracy on the GPQA benchmark?
66% chance
Will OpenAI's next major LLM (after GPT-4) solve more than 2 of the first 5 new Project Euler problems?
45% chance
Will OpenAI's next major LLM (after GPT-4) achieve over 50% resolution rate on the SWE-bench benchmark?
75% chance
Will Llama-4 be (open sourced and) as good as GPT-4?
82% chance
Will there be an LLM (as good as GPT-4) that was trained with 1/100th the energy consumed to train GPT-4, by 2026?
82% chance
Will xAI develop a more capable LLM than GPT-5 by 2026
50% chance
Will an open-source LLM beat or match GPT-4 by the end of 2024?
83% chance
How much time will pass between an LLM being released that beats GPT4 and the next OpenAI LLM being released? (+ANSWERS)
Will the next major LLM by OpenAI use a new tokenizer?
77% chance