GPT-5 vs Llama 4 Scout
Direct spec comparison of GPT-5 (from OpenAI) and Llama 4 Scout (from Meta). Want a 3- or 4-way comparison? Open the multi-model tool →
 GPT-5OpenAI |  Llama 4 ScoutMeta | |
|---|---|---|
| Vendor | OpenAI | Meta |
| Family | GPT | Llama |
| Release date | 2025-08-07 | 2025-04-05 |
| Context window | 400,000 tokens | 10,000,000 tokens |
| Parameters | — | 109B |
| Modality | text, vision, audio | text, vision |
| License | proprietary | Llama 4 Community License |
| Source | proprietary | open weights |
| Description | OpenAI's flagship general-purpose model. Superseded by GPT-5.5 in April 2026. | — |
| Links | ||
| Benchmarks | ||
| MMLU-Pro | 85.1% | — |
| GPQA-D | 87.3% | — |
| HumanEval | 95.2% | — |
| Aider | 85.4% | — |
| AIME-25 | 91.0% | — |
| LiveCB | 74.5% | — |
| MMMU | 74.1% | — |
More like this
Looking for a different head-to-head? Build your own comparison on the multi-model tool.
Or see all GPT-5 details / Llama 4 Scout details.