What is the main reason behind GPT-4o speed improvement relative to GPT-4 base model?
Plus
22
Ṁ13702029
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
This question is managed and resolved by Manifold.
Get
1,000and
3.00
1,0003.00Sort 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
Will the performance jump from GPT4->GPT5 be less than the one from GPT3->GPT4?
71% chance
What is true of the new Japanese GPT-4?
What will the aggregate improvement of GPT5 be over GPT4 in terms of metrics?
157
Is GPT-4 best? (Thru 2025)
52% chance
Was GPT-4 trained in 4 months or less?
59% chance
Will there be a GPT-4.5 model before GPT-5 is released?
13% chance
Will GPT-5 have fewer parameters than GPT-4? (1500M subsidy)
16% chance
Will GPT-4 be trained (roughly) compute-optimally using the best-known scaling laws at the time?
30% chance
GPT-4 performance and compute efficiency from a simple architecture before 2026
17% chance
GPT-4 #5: Will GPT-4 be a dense model?
3% chance