Compare

It was the first release from Claude 3.5 model family. Claude 3.5 Sonnet raises the industry bar for intelligence, outperforming competitor models and Claude 3 Opus on a wide range of evaluations, with the speed and cost of Anthropic's mid-tier models.
vs.
GPT-4, short for Generative Pre-trained Transformer 4, is a large multimodal language model developed by OpenAI as the latest addition to the GPT series of foundational models. It was officially released on March 14, 2023. Users can access GPT-4 through the paid ChatGPT Plus chatbot service, OpenAI's API, and the free Microsoft Copilot chatbot.
Overview
Overview of the AI models
Claude 3.5 Sonnet
GPT-4
Input Context Window
The quantity of tokens that the input context window can accommodate.
200K
tokens
128K
tokens
Release Date
When the model was released.
June 21st, 2024
March 14th, 2023
License
Terms and conditions under which an AI model can be used.
Proprietary
Proprietary
Benchmark
Compare important benchmarks among the AI models
Claude 3.5 Sonnet
GPT-4
MMLU
Measuring Massive Multitask Language Understanding (MMLU) is a benchmark for evaluating the capabilities of language models.
89
86
Throughput
Output tokens per second.
80
tokens/s
20
tokens/s
Latency
Seconds taken to receive the first tokens, measured on an input size of 1000 tokens.
0.8
seconds
0.7
seconds