Gemini Pro, developed by Google, features a context window of 32768 tokens. The model costs 0.0125 cents per thousand tokens for input and 0.0375 cents per thousand tokens for output. It was released on December 13, 2023, and has achieved a score of 47.9 in the MMMU benchmark with a "pass@1" caveat and a score of 71.8 in the MMLU benchmark in a 5-shot scenario.
Overview
Gemini Pro
|
|
|---|---|
|
Provider
The entity that provides this model.
|
Google
|
|
Input Context Window
The number of tokens supported by the input context window.
|
32.8K
characters
|
|
Maximum Output Tokens
The number of tokens that can be generated by the model in a single request.
|
8,192
characters
|
|
Open Source
Whether the model's code is available for public use.
|
No
|
|
Release Date
When the model was first released.
|
2023-12-13
|
|
Knowledge Cut-off Date
When the model's knowledge was last updated.
|
Unknown
|
|
API Providers
The providers that offer this model. (This is not an exhaustive list.)
|
|
|
Empirical Throughput
The number of tokens the model can generate per second.
|
|
Pricing
|
Gemini Pro
|
|
|---|---|
|
Input
Cost of input data provided to the model.
|
Pricing not available.
|
|
Output
Cost of output tokens generated by the model.
|
Pricing not available.
|
Benchmarks
|
Gemini Pro
|
|
|---|---|
|
MMLU
Evaluating LLM knowledge acquisition in zero-shot and few-shot settings.
|
71.8
(5-shot)
|
|
MMMU
A wide ranging multi-discipline and multimodal benchmark.
|
47.9
(pass@1)
|
|
HellaSwag
A challenging sentence completion benchmark.
|
84.7
(10-shot)
|
|
HumanEval
A benchmark to measure functional correctness for synthesizing programs from docstrings.
|
67.7
(0-shot)
|
|
MATH
Benchmark performance on Math problems ranging across 5 levels of difficulty and 7 sub-disciplines.
|
32.6
(4-shot Minerva Prompt)
|
Measure & Improve LLM
Product Performance.
Get Started
© 2023-2024 Context