Compare GPT-3.5 Turbo vs. Mistral Large

Pricing About Us Blog Docs

Book a demo Get Started

Compare

Understand and compare GPT-3.5 Turbo vs. Mistral Large

Generate side-by-side samples for these models in the Context.ai playground

Overview

GPT-3.5 Turbo was released about 1 year before Mistral Large.

	GPT-3.5 Turbo	Mistral Large
Provider The entity that provides this model.	OpenAI	Mistral
Input Context Window The number of tokens supported by the input context window.	4,096 tokens	32K tokens
Maximum Output Tokens The number of tokens that can be generated by the model in a single request.	4,096 tokens	4,096 tokens
Release Date When the model was first released.	November 28th, 2022 over 1 year ago 2022-11-28	February 26th, 2024 4 months ago 2024-02-26

Pricing

GPT-3.5 Turbo is roughly 16x cheaper compared to Mistral Large for input tokens and roughly 5.3x cheaper for output tokens.

	GPT-3.5 Turbo	Mistral Large
Input Cost of input data provided to the model.	$0.50 per million tokens	$8.00 per million tokens
Output Cost of output tokens generated by the model.	$1.50 per million tokens	$8.00 per million tokens

Benchmarks

Compare relevant benchmarks between GPT-3.5 Turbo and Mistral Large.

	GPT-3.5 Turbo	Mistral Large
MMLU Evaluating LLM knowledge acquisition in zero-shot and few-shot settings.	70.0 (5-shot) Source	81.2 (5-shot) Source
MMMU A wide ranging multi-discipline and multimodal benchmark.	Benchmark not available.	Benchmark not available.
HellaSwag A challenging sentence completion benchmark.	85.5 (10-shot) Source	89.2 (10-shot) Source

GPT-3.5 Turbo, developed by OpenAI, features a context window of 4096 tokens. It is priced at 0.05 cents per thousand tokens for input and 0.15 cents per thousand tokens for output. The model was released on November 28, 2022, and has achieved high scores in benchmarks like HellaSwag (85.5 in a 10-shot scenario) and MMLU (70.0 in a 5-shot scenario).

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).

Compare more models