Compare GPT-3.5 Turbo 0125 vs. Mistral Large 2

Pricing About Us Blog Docs

Compare

Understand and compare GPT-3.5 Turbo 0125 vs. Mistral Large 2

Interested in comparing the performance of these models in production? Get a demo of Context.ai

Overview

GPT-3.5 Turbo 0125 was released 6 months before Mistral Large 2.

	GPT-3.5 Turbo 0125	Mistral Large 2
Provider The entity that provides this model.	OpenAI	Mistral
Input Context Window The number of tokens supported by the input context window.	16.4K tokens	128K 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.	January 25th, 2024 8 months ago 2024-01-25	July 24th, 2024 about 2 months ago 2024-07-24
Knowledge Cutoff Limit on the knowledge base used by the model.	September 2021 September 2021	Unknown
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, Snowflake Cortex

Pricing

GPT-3.5 Turbo 0125 is roughly 6.0x cheaper compared to Mistral Large 2 for input and output tokens.

	GPT-3.5 Turbo 0125	Mistral Large 2
Input Cost of input data provided to the model.	$0.50 per million tokens	$3.00 per million tokens
Output Cost of output tokens generated by the model.	$1.50 per million tokens	$9.00 per million tokens

Benchmarks

Compare relevant benchmarks between GPT-3.5 Turbo 0125 and Mistral Large 2.

	GPT-3.5 Turbo 0125	Mistral Large 2
MMLU Evaluating LLM knowledge acquisition in zero-shot and few-shot settings.	Benchmark not available.	84.0 (5-shot) Source
MMMU A wide ranging multi-discipline and multimodal benchmark.	Benchmark not available.	Benchmark not available.
HellaSwag A challenging sentence completion benchmark.	Benchmark not available.	Benchmark not available.
GSM8K Grade-school math problems benchmark.	Benchmark not available.	Benchmark not available.
HumanEval A benchmark to measure functional correctness for synthesizing programs from docstrings.	Benchmark not available.	Benchmark not available.
MATH Benchmark performance on Math problems ranging across 5 levels of difficulty and 7 sub-disciplines.	Benchmark not available.	Benchmark not available.