Compare Claude 3 Haiku vs. GPT-3.5 Turbo

Pricing About Us Blog Docs

Book a demo Get Started

Compare

Understand and compare Claude 3 Haiku vs. GPT-3.5 Turbo

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

Overview

Claude 3 Haiku was released over 1 year after GPT-3.5 Turbo.

	Claude 3 Haiku	GPT-3.5 Turbo
Provider The entity that provides this model.	Anthropic	OpenAI
Input Context Window The number of tokens supported by the input context window.	200K tokens	4,096 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.	March 13th, 2024 about 2 months ago 2024-03-13	November 28th, 2022 over 1 year ago 2022-11-28

Pricing

Claude 3 Haiku is roughly 50.0% cheaper compared to GPT-3.5 Turbo for input tokens and roughly 16.7% cheaper for output tokens.

	Claude 3 Haiku	GPT-3.5 Turbo
Input Cost of input data provided to the model.	$0.25 per million tokens	$0.50 per million tokens
Output Cost of output tokens generated by the model.	$1.25 per million tokens	$1.50 per million tokens

Benchmarks

Compare relevant benchmarks between Claude 3 Haiku and GPT-3.5 Turbo.

	Claude 3 Haiku	GPT-3.5 Turbo
MMLU Evaluating LLM knowledge acquisition in zero-shot and few-shot settings.	76.7 (5-shot CoT) Source	70.0 (5-shot) Source
MMMU A wide ranging multi-discipline and multimodal benchmark.	50.2 Source	Benchmark not available.
HellaSwag A challenging sentence completion benchmark.	85.9 (10-shot) Source	85.5 (10-shot) Source

Claude 3 Haiku, developed by Anthropic, features a context window of 200,000 tokens. The model costs 0.025 cents per thousand tokens for input and 0.125 cents per thousand tokens for output. It was released on March 13, 2024. In benchmarks, it achieved a score of 50.2 in MMMU, 85.9 in HellaSwag in a 10-shot scenario, and 76.7 in MMLU in a 5-shot CoT scenario.

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).

Compare more models