Understand and compare
Gemini Ultra
vs.
Gemini 1.5 Pro
Try
Shepherd
Make it trivial for customers to self-host your SaaS.
Overview
Gemini Ultra
|
Gemini 1.5 Pro
|
|
|---|---|---|
|
Provider
The entity that provides this model.
|
Google
|
Google
|
|
Input Context Window
The number of tokens supported by the input context window.
|
32.8K
characters
|
1M
tokens
|
|
Maximum Output Tokens
The number of tokens that can be generated by the model in a single request.
|
8,192
characters
|
8,192
tokens
|
|
Release Date
When the model was first released.
|
Unknown
|
2024-02-15
|
|
Knowledge Cutoff
Limit on the knowledge base used by the model.
|
Unknown
|
November 2023
|
|
Open Source
|
|
|
|
API Providers
The providers that offer this model. (This is not an exhaustive list.)
|
|
|
Pricing
|
Gemini Ultra
|
Gemini 1.5 Pro
|
|
|---|---|---|
|
Input
Cost of input data provided to the model.
|
Pricing not available.
|
$7.00
per million tokens
|
|
Output
Cost of output tokens generated by the model.
|
Pricing not available.
|
$21.00
per million tokens
|
Benchmarks
Compare relevant benchmarks between Gemini Ultra
and Gemini 1.5 Pro.
|
Gemini Ultra
|
Gemini 1.5 Pro
|
|
|---|---|---|
|
MMLU
Evaluating LLM knowledge acquisition in zero-shot and few-shot settings.
|
83.7
(5-shot)
|
81.9
(5-shot)
|
|
MMMU
A wide ranging multi-discipline and multimodal benchmark.
|
59.4
(0-shot pass@1)
|
58.5
(0-shot)
|
|
HellaSwag
A challenging sentence completion benchmark.
|
Benchmark not available.
|
93.3
(10-shot)
|
|
GSM8K
Grade-school math problems benchmark.
|
88.9
(11-shot)
|
90.8
(11-shot)
|
|
HumanEval
A benchmark to measure functional correctness for synthesizing programs from docstrings.
|
74.4
(0-shot)
|
84.1
(0-shot)
|
|
MATH
Benchmark performance on Math problems ranging across 5 levels of difficulty and 7 sub-disciplines.
|
53.2
(4-shot Minerva Prompt)
|
67.7
(4-shot Minerva Prompt)
|
Gemini Ultra, developed by Google, features a large context window of 32768 tokens. The model has excelled in benchmarks like MMMU with a score of 59.4 in a 0-shot pass@1 scenario and MMLU with a score of 83.7 in a 5-shot scenario.
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 3.1 8B Instruct
o1 Preview 2024-09-12
Claude 2
Measure & Improve LLM
Product Performance.
Get Started
© 2023-2024 Context