Understand and compare
Claude 2.1
vs.
GPT-3.5 Turbo 1106
Try
Shepherd
Make it trivial for customers to self-host your SaaS.
Overview
Claude 2.1 was released
17 days after
GPT-3.5 Turbo 1106.
Claude 2.1
|
GPT-3.5 Turbo 1106
|
|
|---|---|---|
|
Provider
The entity that provides this model.
|
Anthropic
|
OpenAI
|
|
Input Context Window
The number of tokens supported by the input context window.
|
200K
tokens
|
16.4K
tokens
|
|
Maximum Output Tokens
The number of tokens that can be generated by the model in a single request.
|
Not specified.
|
16.4K
tokens
|
|
Release Date
When the model was first released.
|
2023-11-23
|
2023-11-06
|
|
Knowledge Cutoff
Limit on the knowledge base used by the model.
|
Early 2023
|
September 2021
|
|
Open Source
|
|
|
|
API Providers
The providers that offer this model. (This is not an exhaustive list.)
|
|
|
Pricing
Claude 2.1 is
roughly 8.0x more expensive compared
to GPT-3.5 Turbo 1106 for input tokens and
roughly 12x more expensive
for output tokens.
|
Claude 2.1
|
GPT-3.5 Turbo 1106
|
|
|---|---|---|
|
Input
Cost of input data provided to the model.
|
$8.00
per million tokens
|
$1.00
per million tokens
|
|
Output
Cost of output tokens generated by the model.
|
$24.00
per million tokens
|
$2.00
per million tokens
|
Benchmarks
Compare relevant benchmarks between Claude 2.1
and GPT-3.5 Turbo 1106.
|
Claude 2.1
|
GPT-3.5 Turbo 1106
|
|
|---|---|---|
|
MMLU
Evaluating LLM knowledge acquisition in zero-shot and few-shot settings.
|
Benchmark not available.
|
Benchmark not available.
|
|
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.
|
Claude 2.1, developed by Anthropic, features a large context window of 200,000 tokens. The model costs 0.08 cents per thousand tokens for input and 0.24 cents per thousand tokens for output. It was released on November 23, 2023.
GPT-3.5 Turbo 1106, developed by OpenAI, features a context window of 16385 tokens. The model costs 0.1 cents per thousand tokens for input and 0.2 cents per thousand tokens for output. It was released on November 6, 2023.
Llama 2 Chat 70B
Gemini Pro
Measure & Improve LLM
Product Performance.
Get Started
© 2023-2024 Context