	GPT-4o	Gemini Flash
Provider The entity that provides this model.	OpenAI	Google
Input Context Window The number of tokens supported by the input context window.	128K tokens	1M tokens
Maximum Output Tokens The number of tokens that can be generated by the model in a single request.	2,048 tokens	8,192 tokens
Release Date When the model was first released.	May 13th, 2024 7 months ago 2024-05-13	May 14th, 2024 7 months ago 2024-05-14
Knowledge Cutoff Limit on the knowledge base used by the model.	October 2023 October 2023	November 2023 November 2023
Open Source	No	No
API Providers The providers that offer this model. (This is not an exhaustive list.)	OpenAI	Google Cloud Vertex AI Model Garden

	GPT-4o	Gemini Flash
Input Cost of input data provided to the model.	$5.00 per million tokens	$0.13 per million tokens
Output Cost of output tokens generated by the model.	$15.00 per million tokens	$0.38 per million tokens

	GPT-4o	Gemini Flash
MMLU Evaluating LLM knowledge acquisition in zero-shot and few-shot settings.	88.7 (5-shot) Source	78.9 (5-shot) Source
MMMU A wide ranging multi-discipline and multimodal benchmark.	69.1 Source	56.1 (0-shot pass@1) Source
HellaSwag A challenging sentence completion benchmark.	Benchmark not available.	86.5 (10-shot) Source
GSM8K Grade-school math problems benchmark.	Benchmark not available.	86.2 (11-shot) Source
HumanEval A benchmark to measure functional correctness for synthesizing programs from docstrings.	Benchmark not available.	74.3 (0-shot) Source
MATH Benchmark performance on Math problems ranging across 5 levels of difficulty and 7 sub-disciplines.	76.6 (0-shot) Source	54.9 (4-shot Minerva Prompt) Source