Understand and compare
Gemini 1.5 Pro
vs.
GPT-4
Try
Podial
Turn your documents into engaging podcast discussions.
Overview
Gemini 1.5 Pro was released
11 months after
GPT-4.
Gemini 1.5 Pro
|
GPT-4
|
|
|---|---|---|
|
Provider
The entity that provides this model.
|
Google
|
OpenAI
|
|
Input Context Window
The number of tokens supported by the input context window.
|
1M
tokens
|
8,192
tokens
|
|
Maximum Output Tokens
The number of tokens that can be generated by the model in a single request.
|
8,192
tokens
|
8,192
tokens
|
|
Release Date
When the model was first released.
|
2024-02-15
|
2023-03-14
|
|
Knowledge Cutoff
Limit on the knowledge base used by the model.
|
November 2023
|
September 2021
|
|
Open Source
|
|
|
|
API Providers
The providers that offer this model. (This is not an exhaustive list.)
|
|
|
Pricing
Gemini 1.5 Pro is
roughly 4.3x cheaper compared
to GPT-4 for input tokens and
roughly 2.9x cheaper
for output tokens.
|
Gemini 1.5 Pro
|
GPT-4
|
|
|---|---|---|
|
Input
Cost of input data provided to the model.
|
$7.00
per million tokens
|
$30.00
per million tokens
|
|
Output
Cost of output tokens generated by the model.
|
$21.00
per million tokens
|
$60.00
per million tokens
|
Benchmarks
Compare relevant benchmarks between Gemini 1.5 Pro
and GPT-4.
|
Gemini 1.5 Pro
|
GPT-4
|
|
|---|---|---|
|
MMLU
Evaluating LLM knowledge acquisition in zero-shot and few-shot settings.
|
81.9
(5-shot)
|
86.4
(5-shot)
|
|
MMMU
A wide ranging multi-discipline and multimodal benchmark.
|
58.5
(0-shot)
|
34.9
|
|
HellaSwag
A challenging sentence completion benchmark.
|
93.3
(10-shot)
|
95.3
(10-shot)
|
|
GSM8K
Grade-school math problems benchmark.
|
90.8
(11-shot)
|
92.0
(5-shot)
|
|
HumanEval
A benchmark to measure functional correctness for synthesizing programs from docstrings.
|
84.1
(0-shot)
|
67.0
(0-shot)
|
|
MATH
Benchmark performance on Math problems ranging across 5 levels of difficulty and 7 sub-disciplines.
|
67.7
(4-shot Minerva Prompt)
|
Benchmark not available.
|
Gemini 1.5 Pro by Google features a vast context window of 1,000,000 tokens. The model is priced at 0.7 cents per thousand tokens for input and 2.1 cents per thousand tokens for output. It was launched on February 15, 2024. In benchmark tests, it achieved a score of 58.5 in MMMU with a 0-shot scenario and 81.9 in MMLU with a 5-shot scenario.
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.
Llama 3.1 405B Instruct
Claude 2.1
Measure & Improve LLM
Product Performance.
Get Started
© 2023-2024 Context