Compare GPT-4 vs. Llama 3 8B Instruct

Pricing About Us Blog Docs

Book a demo

Compare

Understand and compare GPT-4 vs. Llama 3 8B Instruct

Try Podial

Turn your documents into engaging podcast discussions.

Overview

GPT-4 was released about 1 year before Llama 3 8B Instruct.

	GPT-4	Llama 3 8B Instruct
Provider The entity that provides this model.	OpenAI	Meta
Input Context Window The number of tokens supported by the input context window.	8,192 tokens	8,000 tokens
Maximum Output Tokens The number of tokens that can be generated by the model in a single request.	8,192 tokens	2,048 tokens
Release Date When the model was first released.	March 14th, 2023 almost 2 years ago 2023-03-14	April 18th, 2024 8 months ago 2024-04-18
Knowledge Cutoff Limit on the knowledge base used by the model.	September 2021 September 2021	March 2023 March 2023
Open Source	No	Yes
API Providers The providers that offer this model. (This is not an exhaustive list.)	OpenAI	Azure AI, AWS Bedrock, Google Cloud Vertex AI Model Garden, NVIDIA NIM, IBM watsonx

Pricing

	GPT-4	Llama 3 8B Instruct
Input Cost of input data provided to the model.	$30.00 per million tokens	Pricing not available.
Output Cost of output tokens generated by the model.	$60.00 per million tokens	Pricing not available.

Benchmarks

Compare relevant benchmarks between GPT-4 and Llama 3 8B Instruct.

	GPT-4	Llama 3 8B Instruct
MMLU Evaluating LLM knowledge acquisition in zero-shot and few-shot settings.	86.4 (5-shot) Source	68.4 (5-shot) Source
MMMU A wide ranging multi-discipline and multimodal benchmark.	34.9 Source	Benchmark not available.
HellaSwag A challenging sentence completion benchmark.	95.3 (10-shot) Source	Benchmark not available.
GSM8K Grade-school math problems benchmark.	92.0 (5-shot) Source	80.6 (8-shot) Source
HumanEval A benchmark to measure functional correctness for synthesizing programs from docstrings.	67.0 (0-shot) Source	Benchmark not available.
MATH Benchmark performance on Math problems ranging across 5 levels of difficulty and 7 sub-disciplines.	Benchmark not available.	29.1 (0-shot) Source

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 8B Instruct, developed by Meta, features a context window of 8000 tokens. The model was released on April 18, 2024, and achieved a score of 68.4 in the MMLU benchmark.

Compare more models