Compare AI models

Specifications
Parameters
16B—
Context window
32k128k
API pricing
Input price
—$2.50
Output price
—$10.00
Cached input price
—$1.25
Cheapest input
—$2.50Azure
Cheapest output
—$10.00Azure
—$1,000OpenAI list price
Benchmarks
HumanEval
57.3%91%
MATH
27.9%76.6%
MMLU
55.7%87.2%
Overview
CompanyDeepSeekOpenAI
Release dateMay 16 2024May 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GPT-4o leads DeepSeek V2 Lite on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). Only GPT-4o has a verified first-party price for an available API: $2.50 per million input tokens and $10.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek V2 Lite. GPT-4o shipped 3 days before DeepSeek V2 Lite, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (DeepSeek V2 Lite) vs 128k (GPT-4o). DeepSeek V2 Lite is open weight, while GPT-4o is closed.

On HumanEval, GPT-4o leads at 91% vs DeepSeek V2 Lite at 57.3%. On MATH, GPT-4o leads at 76.6% vs DeepSeek V2 Lite at 27.9%. On MMLU, GPT-4o leads at 87.2% vs DeepSeek V2 Lite at 55.7%.