LLaMA 4 ScoutvsGPT-5-Codex

LLaMA 4 Scout
GPT-5-Codex
API pricing
Cheapest input
$0.10DeepInfra
Cheapest output
$0.30DeepInfra
Benchmarks
BullshitBench v2
19%39%
Overview
CompanyMetaOpenAI
Release dateApr 5 2025Sep 15 2025
AccessOpen WeightProprietary

Other comparisons

LLaMA 4 ScoutvsClaude Opus 5GPT-5-CodexvsClaude Opus 5LLaMA 4 ScoutvsGemini 3.7 FlashGPT-5-CodexvsGemini 3.7 FlashLLaMA 4 ScoutvsGrok 4.6GPT-5-CodexvsGrok 4.6LLaMA 4 ScoutvsDeepSeek-V4-Pro-0813GPT-5-CodexvsDeepSeek-V4-Pro-0813LLaMA 4 ScoutvsMistral Medium 3.5GPT-5-CodexvsMistral Medium 3.5LLaMA 4 ScoutvsKimi K3GPT-5-CodexvsKimi K3

Frequently asked questions

GPT-5-Codex leads LLaMA 4 Scout on 1 of the 1 benchmark they both report (BullshitBench v2). LLaMA 4 Scout shipped 163 days before GPT-5-Codex, so benchmark comparisons should account for the intervening progress.

LLaMA 4 Scout is open weight, while GPT-5-Codex is proprietary.

On BullshitBench v2, GPT-5-Codex leads at 39% vs LLaMA 4 Scout at 19%.

LLaMA 4 Scout was released by Meta on Apr 5 2025.

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

LLaMA 4 Scout is an open weight model released by Meta. GPT-5-Codex is a proprietary model released by OpenAI.