GPT-5 Codex vs Llama 4 Scout
OpenAI vs Meta — benchmarks, pricing, and capabilities side by side.
- •GPT-5 Codex has the higher intelligence index (87.1 vs 58.9)
- •Llama 4 Scout is cheaper ($0.08 vs $1.25 per 1M input)
- •Llama 4 Scout is faster
- •Llama 4 Scout has a larger context window (10M)
| GPT-5 Codex | Llama 4 Scout | |
|---|---|---|
| Intelligence index | 87.1 | 58.9 |
| Developer | OpenAI | Meta |
| Type | Multimodal | Multimodal |
| Access | API only | Open weights |
| Context window | 400,000 tokens | 10,000,000 tokens |
| Input price | $1.25 / 1M | $0.08 / 1M |
| Output price | $10.00 / 1M | $0.30 / 1M |
| Speed | 180 tok/s | 776 tok/s |
| Released | September 23, 2025 | April 5, 2025 |
| Parameters | — | 109B total / 17B active (MoE) |
| Input modalities | Text, Image | Text, Image |
| Output modalities | Text | Text |
Shared benchmarks
GPT-5 Codex
Llama 4 Scout
AIME 2025
98.7
14
GPQA Diamond
83.7
57.2
Humanity’s Last Exam
25.6
4.3
LiveCodeBench
84
32.8
MMLU-Pro
86.5
74.3