GPT-5 Codex vs Llama 4 Maverick
OpenAI vs Meta — benchmarks, pricing, and capabilities side by side.
- •GPT-5 Codex has the higher intelligence index (87.1 vs 63.9)
- •Llama 4 Maverick is cheaper ($0.15 vs $1.25 per 1M input)
- •Llama 4 Maverick is faster
- •Llama 4 Maverick has a larger context window (1M)
| GPT-5 Codex | Llama 4 Maverick | |
|---|---|---|
| Intelligence index | 87.1 | 63.9 |
| Developer | OpenAI | Meta |
| Type | Multimodal | Multimodal |
| Access | API only | Open weights |
| Context window | 400,000 tokens | 1,048,576 tokens |
| Input price | $1.25 / 1M | $0.15 / 1M |
| Output price | $10.00 / 1M | $0.60 / 1M |
| Speed | 180 tok/s | 639 tok/s |
| Released | September 23, 2025 | April 5, 2025 |
| Parameters | — | 400B total / 17B active (MoE) |
| Input modalities | Text, Image | Text, Image |
| Output modalities | Text | Text |
Shared benchmarks
GPT-5 Codex
Llama 4 Maverick
AIME 2025
98.7
19.3
GPQA Diamond
83.7
69.8
Humanity’s Last Exam
25.6
4.8
LiveCodeBench
84
43.4
MMLU-Pro
86.5
80.5
SWE-bench Verified
74.5
30