![](/_next/image?url=https%3A%2F%2Fstorage.googleapis.com%2Fmantic-markets.appspot.com%2Fcontract-images%2FIhorKendiukhov%2Fb33f274cd22d.jpg&w=3840&q=75)
What is the main reason behind GPT-4o speed improvement relative to GPT-4 base model?
Basic
22
Ṁ1.4k2029
1D
1W
1M
ALL
69%
Smaller model size (hence, architecture/algorithm improvements)
40%
Something related to low-level computation efficiency (for example, optimized frameworks)
27%
More/better hardware allocated
23%
Other
15%
Better coarser-grained tokenizer
Get Ṁ600 play money
Related questions
Sort by:
@MaxHarms Correct. In very ambiguous situations, 2 options may resolve YES, but I expect this to happen in only extreme cases.
Related questions
Related questions
What will be true about GPT-4.5?
Will the performance jump from GPT4->GPT5 be less than the one from GPT3->GPT4?
76% chance
Will there be a GPT-4.5 model before GPT-5 is released?
45% chance
What will the aggregate improvement of GPT5 be over GPT4 in terms of metrics?
157
Will GPT-4 be trained (roughly) compute-optimally using the best-known scaling laws at the time?
30% chance
Was GPT-4 trained in 4 months or less?
59% chance
What is true of the new Japanese GPT-4?
Will we have an open-source model better than GPT-4-Turbo before 2025?
69% chance
Is GPT-4 best? (Thru 2025)
52% chance
Will Llama 3 400B be better than GPT-4?
78% chance