When will an open-source LLM be released with a better performance than GPT-4?
6
137
Ṁ304Ṁ395
2026
1D
1W
1M
ALL
1.4%
Q3 2023
3%
Q4 2023
9%
Q1-Q2 2024
34%
Q3-Q4 2024
30%
2025
13%
2026
10%
"Better" is a moving target since LLMs tend to be compared on large suites of tasks and datasets, and over time the consensus of effective benchmarks changes.
But the question will resolve positively if it shows matching or better performance on at least 3 benchmarks that are reasonably standard at the time and somewhat general purpose (not specialized on maths, coding or some other narrow class of reasoning).
Open-source means that both the code and the weights are openly available, regardless of the license.
Get Ṁ200 play money
Related questions
Will any open source LLM with <20 billion parameters outperform GPT-4 on most language benchmarks by the end of 2024?
15% chance
How much time will pass between an LLM being released that beats GPT4 and the next OpenAI LLM being released? (+ANSWERS)
Will it be possible to run an LLM of GPT-4 (or higher) capability on a portable device by 2027?
47% chance
Will there be 20+ LLMs that match or outperform GPT-3.5's performance by the end of 2024?
89% chance
Will we have an open-source model that is equivalent GPT-4 by end of 2025?
84% chance
Will an open-source fully functional Auto-GPT like LLM exist by the end of 2025?
89% chance
When will GPT-4 be open-sourced?
Will a 15 billion parameter LLM match or outperform GPT4 in 2024?
8% chance
Will an uncensored open-source LLM model comparable to 2023 GPT4 be available to the public by the end of 2025?
84% chance
Will the 400B+ open source Llama 3 model rank higher than GPT-4-Turbo-2024-04-09 on the lmsys leaderboard?
52% chance