Claude 3.5 SonnetvsLLaMA 3.1

Claude 3.5 Sonnet
LLaMA 3.1
API pricing
Cheapest input
$0.02DeepInfra
Cheapest output
$0.04DeepInfra
Benchmarks
BullshitBench v2
46%14%
Benchmarks
SWE-Bench Verified
33.4%
GPQA Diamond
59.4%
Overview
CompanyAnthropicMeta
Release dateJun 20 2024Jul 23 2024
AccessProprietaryOpen Weight

Other comparisons

Claude 3.5 SonnetvsGPT-6 AstraLLaMA 3.1vsGPT-6 AstraClaude 3.5 SonnetvsGemini 3.8 FlashLLaMA 3.1vsGemini 3.8 FlashClaude 3.5 SonnetvsGrok 4.6LLaMA 3.1vsGrok 4.6Claude 3.5 SonnetvsDeepSeek-V4.1-FlashLLaMA 3.1vsDeepSeek-V4.1-FlashClaude 3.5 SonnetvsMistral Medium 3.5LLaMA 3.1vsMistral Medium 3.5Claude 3.5 SonnetvsKimi K3LLaMA 3.1vsKimi K3

Frequently asked questions

Claude 3.5 Sonnet leads LLaMA 3.1 on 1 of the 1 benchmark they both report (BullshitBench v2). Claude 3.5 Sonnet shipped 33 days before LLaMA 3.1, so benchmark comparisons should account for the intervening progress.

Claude 3.5 Sonnet is proprietary, while LLaMA 3.1 is open weight.

On BullshitBench v2, Claude 3.5 Sonnet leads at 46% vs LLaMA 3.1 at 14%.