Compare to
Overview
GPT-4 was released 11 months before GPT-3.5 Turbo 0125.
GPT-4
GPT-3.5 Turbo 0125
Provider
The entity that provides this model.
OpenAI
OpenAI
Input Context Window
The number of tokens supported by the input context window.
8,192
tokens
16.4K
tokens
Maximum Output Tokens
The number of tokens that can be generated by the model in a single request.
8,192
tokens
4,096
tokens
Release Date
When the model was first released.
2023-03-14
2024-01-25
Knowledge Cutoff
Limit on the knowledge base used by the model.
September 2021
September 2021
Open Source
API Providers
The providers that offer this model. (This is not an exhaustive list.)
Pricing
GPT-4 is roughly 60x more expensive compared to GPT-3.5 Turbo 0125 for input tokens and roughly 40x more expensive for output tokens.
GPT-4
GPT-3.5 Turbo 0125
Input
Cost of input data provided to the model.
$30.00
per million tokens
$0.50
per million tokens
Output
Cost of output tokens generated by the model.
$60.00
per million tokens
$1.50
per million tokens
Benchmarks
Compare relevant benchmarks between GPT-4 and GPT-3.5 Turbo 0125.
GPT-4
GPT-3.5 Turbo 0125
MMLU
Evaluating LLM knowledge acquisition in zero-shot and few-shot settings.
86.4
(5-shot)
Benchmark not available.
MMMU
A wide ranging multi-discipline and multimodal benchmark.
34.9
Benchmark not available.
HellaSwag
A challenging sentence completion benchmark.
95.3
(10-shot)
Benchmark not available.
GSM8K
Grade-school math problems benchmark.
92.0
(5-shot)
Benchmark not available.
HumanEval
A benchmark to measure functional correctness for synthesizing programs from docstrings.
67.0
(0-shot)
Benchmark not available.
MATH
Benchmark performance on Math problems ranging across 5 levels of difficulty and 7 sub-disciplines.
Benchmark not available.
Benchmark not available.
Measure & Improve LLM Product Performance.
Get Started