Understand and compare
GPT-3.5 Turbo 1106
vs.
Gemini 1.5 Pro
Try
Shepherd
Make it trivial for customers to self-host your SaaS.
Overview
GPT-3.5 Turbo 1106 was released
3 months before
Gemini 1.5 Pro.
GPT-3.5 Turbo 1106
|
Gemini 1.5 Pro
|
|
|---|---|---|
|
Provider
The entity that provides this model.
|
OpenAI
|
Google
|
|
Input Context Window
The number of tokens supported by the input context window.
|
16.4K
tokens
|
1M
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.
|
2023-11-06
|
2024-02-15
|
|
Knowledge Cutoff
Limit on the knowledge base used by the model.
|
September 2021
|
November 2023
|
|
Open Source
|
|
|
|
API Providers
The providers that offer this model. (This is not an exhaustive list.)
|
|
|
Pricing
GPT-3.5 Turbo 1106 is
roughly 7.0x cheaper compared
to Gemini 1.5 Pro for input tokens and
roughly 10x cheaper
for output tokens.
|
GPT-3.5 Turbo 1106
|
Gemini 1.5 Pro
|
|
|---|---|---|
|
Input
Cost of input data provided to the model.
|
$1.00
per million tokens
|
$7.00
per million tokens
|
|
Output
Cost of output tokens generated by the model.
|
$2.00
per million tokens
|
$21.00
per million tokens
|
Benchmarks
Compare relevant benchmarks between GPT-3.5 Turbo 1106
and Gemini 1.5 Pro.
|
GPT-3.5 Turbo 1106
|
Gemini 1.5 Pro
|
|
|---|---|---|
|
MMLU
Evaluating LLM knowledge acquisition in zero-shot and few-shot settings.
|
Benchmark not available.
|
81.9
(5-shot)
|
|
MMMU
A wide ranging multi-discipline and multimodal benchmark.
|
Benchmark not available.
|
58.5
(0-shot)
|
|
HellaSwag
A challenging sentence completion benchmark.
|
Benchmark not available.
|
93.3
(10-shot)
|
|
GSM8K
Grade-school math problems benchmark.
|
Benchmark not available.
|
90.8
(11-shot)
|
|
HumanEval
A benchmark to measure functional correctness for synthesizing programs from docstrings.
|
Benchmark not available.
|
84.1
(0-shot)
|
|
MATH
Benchmark performance on Math problems ranging across 5 levels of difficulty and 7 sub-disciplines.
|
Benchmark not available.
|
67.7
(4-shot Minerva Prompt)
|
GPT-3.5 Turbo 1106, developed by OpenAI, features a context window of 16385 tokens. The model costs 0.1 cents per thousand tokens for input and 0.2 cents per thousand tokens for output. It was released on November 6, 2023.
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.
Llama 2 Chat 13B
Claude 3 Sonnet
Measure & Improve LLM
Product Performance.
Get Started
© 2023-2024 Context