Compare Mistral Large vs. GPT-4

Pricing About Us Blog Docs

Book a demo

Compare

Understand and compare Mistral Large vs. GPT-4

Try Podial

Turn your documents into engaging podcast discussions.

Overview

Mistral Large was released 12 months after GPT-4.

	Mistral Large	GPT-4
Provider The entity that provides this model.	Mistral	OpenAI
Input Context Window The number of tokens supported by the input context window.	32K tokens	8,192 tokens
Maximum Output Tokens The number of tokens that can be generated by the model in a single request.	4,096 tokens	8,192 tokens
Release Date When the model was first released.	February 26th, 2024 9 months ago 2024-02-26	March 14th, 2023 over 1 year ago 2023-03-14
Knowledge Cutoff Limit on the knowledge base used by the model.	Unknown	September 2021 September 2021
Open Source	Yes	No
API Providers The providers that offer this model. (This is not an exhaustive list.)	Azure AI, AWS Bedrock, Google Cloud Vertex AI Model Garden, Snowflake Cortex	OpenAI

Pricing

Mistral Large is roughly 3.7x cheaper compared to GPT-4 for input tokens and roughly 7.5x cheaper for output tokens.

	Mistral Large	GPT-4
Input Cost of input data provided to the model.	$8.00 per million tokens	$30.00 per million tokens
Output Cost of output tokens generated by the model.	$8.00 per million tokens	$60.00 per million tokens

Benchmarks

Compare relevant benchmarks between Mistral Large and GPT-4.

	Mistral Large	GPT-4
MMLU Evaluating LLM knowledge acquisition in zero-shot and few-shot settings.	81.2 (5-shot) Source	86.4 (5-shot) Source
MMMU A wide ranging multi-discipline and multimodal benchmark.	Benchmark not available.	34.9 Source
HellaSwag A challenging sentence completion benchmark.	89.2 (10-shot) Source	95.3 (10-shot) Source
GSM8K Grade-school math problems benchmark.	Benchmark not available.	92.0 (5-shot) Source
HumanEval A benchmark to measure functional correctness for synthesizing programs from docstrings.	Benchmark not available.	67.0 (0-shot) Source
MATH Benchmark performance on Math problems ranging across 5 levels of difficulty and 7 sub-disciplines.	Benchmark not available.	Benchmark not available.

Mistral Large, developed by Mistral, features a context window of 32000 tokens. The model is priced at 0.8 cents per thousand tokens for both input and output. It was released on February 26, 2024, and has achieved impressive scores in benchmarks like MMLU (81.2 in a 5-shot scenario) and HellaSwag (89.2 in a 10-shot scenario).

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.

Compare more models