Compare AI models

Specifications
Parameters
16B—
Context window
32k8k
API pricing
Cheapest input
—$30.00Azure
Cheapest output
—$60.00Azure
—$9,000Azure
Benchmarks
HumanEval
57.3%67%
MMLU
55.7%86.4%
GSM8K
72%92%
Overview
CompanyDeepSeekOpenAI
Release dateMay 16 2024Mar 14 2023
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GPT-4 leads DeepSeek V2 Lite on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). GPT-4 shipped 429 days before DeepSeek V2 Lite, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (DeepSeek V2 Lite) vs 8k (GPT-4). DeepSeek V2 Lite is open weight, while GPT-4 is closed.

On HumanEval, GPT-4 leads at 67% vs DeepSeek V2 Lite at 57.3%. On MMLU, GPT-4 leads at 86.4% vs DeepSeek V2 Lite at 55.7%. On GSM8K, GPT-4 leads at 92% vs DeepSeek V2 Lite at 72%.