Compare AI models

Specifications
Parameters
—16B
Context window
200k32k
Benchmarks
HumanEval
73%57.3%
MMLU
81.5%55.7%
GSM8K
92.3%72%
Overview
CompanyAnthropicDeepSeek
Release dateMar 4 2024May 16 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 3 Sonnet leads DeepSeek V2 Lite on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Claude 3 Sonnet shipped 73 days before DeepSeek V2 Lite, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3 Sonnet) vs 32k (DeepSeek V2 Lite). Claude 3 Sonnet is closed, while DeepSeek V2 Lite is open weight.

On HumanEval, Claude 3 Sonnet leads at 73% vs DeepSeek V2 Lite at 57.3%. On MMLU, Claude 3 Sonnet leads at 81.5% vs DeepSeek V2 Lite at 55.7%. On GSM8K, Claude 3 Sonnet leads at 92.3% vs DeepSeek V2 Lite at 72%.