LLaMA 3.1vsGPT-5-Codex

LLaMA 3.1
GPT-5-Codex
API pricing
Cheapest input
$0.02Novita
Cheapest output
$0.05Novita
Benchmarks
BullshitBench v2
14%39%
Overview
CompanyMetaOpenAI
Release dateJul 23 2024Sep 15 2025
AccessOpen WeightProprietary

Other comparisons

LLaMA 3.1vsClaude Opus 5GPT-5-CodexvsClaude Opus 5LLaMA 3.1vsGemini 3.7 FlashGPT-5-CodexvsGemini 3.7 FlashLLaMA 3.1vsGrok 4.6GPT-5-CodexvsGrok 4.6LLaMA 3.1vsDeepSeek-V4-Pro-0813GPT-5-CodexvsDeepSeek-V4-Pro-0813LLaMA 3.1vsMistral Medium 3.5GPT-5-CodexvsMistral Medium 3.5LLaMA 3.1vsKimi K3GPT-5-CodexvsKimi K3

Frequently asked questions

GPT-5-Codex leads LLaMA 3.1 on 1 of the 1 benchmark they both report (BullshitBench v2). LLaMA 3.1 shipped 419 days before GPT-5-Codex, so benchmark comparisons should account for the intervening progress.

LLaMA 3.1 is open weight, while GPT-5-Codex is proprietary.

On BullshitBench v2, GPT-5-Codex leads at 39% vs LLaMA 3.1 at 14%.

LLaMA 3.1 was released by Meta on Jul 23 2024.

GPT-5-Codex was released by OpenAI on Sep 15 2025.

LLaMA 3.1 is an open weight model released by Meta. GPT-5-Codex is a proprietary model released by OpenAI.