Understand and compare
GPT-3.5 Turbo 16K
vs.
GPT-4
Overview
GPT-3.5 Turbo 16K was released
3 months after
GPT-4.
GPT-3.5 Turbo 16K
|
GPT-4
|
|
---|---|---|
Provider
The entity that provides this model.
|
OpenAI
|
OpenAI
|
Input Context Window
The number of tokens supported by the input context window.
|
16.4K
tokens
|
8,192
tokens
|
Maximum Output Tokens
The number of tokens that can be generated by the model in a single request.
|
16.4K
tokens
|
8,192
tokens
|
Release Date
When the model was first released.
|
2023-06-13
|
2023-03-14
|
Pricing
GPT-3.5 Turbo 16K is
roughly 10.0x cheaper compared
to GPT-4 for input tokens and
roughly 15x cheaper
for output tokens.
GPT-3.5 Turbo 16K
|
GPT-4
|
|
---|---|---|
Input
Cost of input data provided to the model.
|
$3.00
per million tokens
|
$30.00
per million tokens
|
Output
Cost of output tokens generated by the model.
|
$4.00
per million tokens
|
$60.00
per million tokens
|
Benchmarks
Compare relevant benchmarks between GPT-3.5 Turbo 16K
and GPT-4.
GPT-3.5 Turbo 16K
|
GPT-4
|
|
---|---|---|
MMLU
Evaluating LLM knowledge acquisition in zero-shot and few-shot settings.
|
Benchmark not available.
|
86.4
(5-shot)
|
MMMU
A wide ranging multi-discipline and multimodal benchmark.
|
Benchmark not available.
|
34.9
|
HellaSwag
A challenging sentence completion benchmark.
|
Benchmark not available.
|
95.3
(10-shot)
|
GPT-3.5 Turbo 16K, developed by OpenAI, features a context window of 16384 tokens. The model costs 0.3 cents per thousand tokens for input and 0.4 cents per thousand tokens for output. It was released on June 13, 2023.
GPT-4, developed by OpenAI, features a context window of 8192 tokens. The model costs 3.0 cents per thousand tokens for input and 6.0 cents per thousand tokens for output. It was released on March 14, 2023, and has achieved impressive scores in benchmarks like HellaSwag with a score of 95.3 in a 10-shot scenario and MMLU with a score of 86.4 in a 5-shot scenario.
Measure & Improve LLM
Product Performance.
Get Started