Gemini 2.5 Flash vs GPT-5.2-Codex
Google vs OpenAI — benchmarks, pricing, and capabilities side by side.
- •GPT-5.2-Codex has the higher intelligence index (89.9 vs 73.1)
- •Gemini 2.5 Flash is cheaper ($0.30 vs $1.75 per 1M input)
- •GPT-5.2-Codex is faster
- •Gemini 2.5 Flash has a larger context window (1M)
| Gemini 2.5 Flash | GPT-5.2-Codex | |
|---|---|---|
| Intelligence index | 73.1 | 89.9 |
| Developer | OpenAI | |
| Type | Multimodal | Multimodal |
| Access | API only | API only |
| Context window | 1,048,576 tokens | 400,000 tokens |
| Input price | $0.30 / 1M | $1.75 / 1M |
| Output price | $2.50 / 1M | $14.00 / 1M |
| Speed | 85 tok/s | 106 tok/s |
| Released | April 17, 2025 | January 14, 2026 |
| Parameters | — | — |
| Input modalities | Text, Image, Audio, Video | Text, Image |
| Output modalities | Text | Text |
Shared benchmarks
Gemini 2.5 Flash
GPT-5.2-Codex
GPQA Diamond
82.8
89.9
Humanity’s Last Exam
11
33.5