LLaMA 3.1 vs GPT-5-Codex
Meta LLaMA 3.1 | OpenAI GPT-5-Codex | |
|---|---|---|
| Overview | ||
| Company | Meta | OpenAI |
| Release date | Jul 23 2024 | Sep 15 2025 |
| Access | Open Weight | Proprietary |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 14% | 39%Best |
| Timeline | ||
| Release gap | LLaMA 3.1 shipped 419 days before GPT-5-Codex | |
Which is better: LLaMA 3.1 or GPT-5-Codex?
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%.
Frequently asked questions
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.
Other comparisons
LLaMA 3.1 vs Claude Sonnet 5GPT-5-Codex vs Claude Sonnet 5LLaMA 3.1 vs Gemini 3.5 FlashGPT-5-Codex vs Gemini 3.5 FlashLLaMA 3.1 vs Grok 4.5GPT-5-Codex vs Grok 4.5LLaMA 3.1 vs DeepSeek-V4-ProGPT-5-Codex vs DeepSeek-V4-ProLLaMA 3.1 vs Mistral Medium 3.5GPT-5-Codex vs Mistral Medium 3.5LLaMA 3.1 vs Kimi K2.7 CodeGPT-5-Codex vs Kimi K2.7 Code