Compare AI models

Specifications
Parameters
16B—
Context window
32k128k
Benchmarks
HumanEval
57.3%88.6%
MMLU
55.7%90.8%
Overview
CompanyDeepSeekOpenAI
Release dateMay 16 2024Feb 27 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GPT-4.5 leads DeepSeek V2 Lite on 2 of the 2 benchmarks they both report (HumanEval, MMLU). DeepSeek V2 Lite shipped 287 days before GPT-4.5, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (DeepSeek V2 Lite) vs 128k (GPT-4.5). DeepSeek V2 Lite is open weight, while GPT-4.5 is closed.

On HumanEval, GPT-4.5 leads at 88.6% vs DeepSeek V2 Lite at 57.3%. On MMLU, GPT-4.5 leads at 90.8% vs DeepSeek V2 Lite at 55.7%.