GPT-4 32K vs GPT-4o (Which is Better in 2024?)

Compare

Comparative Analysis: GPT-4 32K vs. GPT-4o

Interested in trying out these models in one collaborative workspace?Try out Flamingo.ai for free

Overview

GPT-4 32K was released 1 year before GPT-4o.

	GPT-4 32K	GPT-4o
Model Provider The organization behind this AI's development	OpenAI	OpenAI
Input Context Window Maximum input tokens this model can process at once	32.8K tokens	128.0K tokens
Output Token Limit Maximum output tokens this model can generate at once	Not specified tokens	2048 tokens
Release Date When this model first became publicly available	March 14, 2023 1 year ago March 14th, 2023	May 13, 2024 5 months ago May 13th, 2024

Pricing

GPT-4 32K is roughly 12.0x more expensive compared to GPT-4o for input tokens and roughly 8.0x more expensive for output tokens.

	GPT-4 32K	GPT-4o
Input Token Cost Cost per million tokens fed into the model	$60.00 per million tokens	$5.00 per million tokens
Output Token Cost Cost per million tokens generated by the model	$120.00 per million tokens	$15.00 per million tokens

Benchmarks

Compare relevant benchmarks between GPT-4 32K and GPT-4o.

	GPT-4 32K	GPT-4o
MMLU Measures model's ability to answer questions across various domains	Benchmark not available.	88.7 (5-shot) Source
MMMU Evaluates model's performance across diverse tasks and data types	Benchmark not available.	69.1 Source
HellaSwag Assesses the model's ability to understand everyday scenarios	Benchmark not available.	Benchmark not available.

GPT-4 32K, developed by OpenAI, features a context window (the maximum amount of text the model can consider at once) of 32.8K tokens (individual units of text or subwords). The model costs $60.00 per million tokens for input (text fed into the model) and $120.00 per million tokens for output (text generated by the model). It was made publicly available on March 14th, 2023.

GPT-4o, developed by OpenAI, features a context window (the maximum amount of text the model can consider at once) of 128.0K tokens (individual units of text or subwords). The model costs $5.00 per million tokens for input (text fed into the model) and $15.00 per million tokens for output (text generated by the model). It was made publicly available on May 13th, 2024. It has achieved impressive scores in benchmarks (standardized tests for AI models) like MMLU (Massive Multitask Language Understanding, a test of general knowledge) with a score of 88.7 in a 5-shot scenario (a specific testing condition). OpenAI logo