GPT-5 Codex vs Sonar
OpenAI vs Perplexity — benchmarks, pricing, and capabilities side by side.
- •GPT-5 Codex has the higher intelligence index (87.1 vs 56.8)
- •Sonar is cheaper ($1.00 vs $1.25 per 1M input)
- •GPT-5 Codex has a larger context window (400K)
| GPT-5 Codex | Sonar | |
|---|---|---|
| Intelligence index | 87.1 | 56.8 |
| Developer | OpenAI | Perplexity |
| Type | Multimodal | Multimodal |
| Access | API only | API only |
| Context window | 400,000 tokens | 127,072 tokens |
| Input price | $1.25 / 1M | $1.00 / 1M |
| Output price | $10.00 / 1M | $1.00 / 1M |
| Speed | 180 tok/s | — |
| Released | September 23, 2025 | January 27, 2025 |
| Parameters | — | — |
| Input modalities | Text, Image | Text, Image |
| Output modalities | Text | Text |
Shared benchmarks
GPT-5 Codex
Sonar
GPQA Diamond
83.7
47.1
Humanity’s Last Exam
25.6
7.3
LiveCodeBench
84
29.5
MMLU-Pro
86.5
68.9