Gemini 3 Flash vs GPT-5.1-Codex
Google vs OpenAI — benchmarks, pricing, and capabilities side by side.
- •Gemini 3 Flash has the higher intelligence index (90.2 vs 88.2)
- •Gemini 3 Flash is cheaper ($0.50 vs $1.25 per 1M input)
- •Gemini 3 Flash is faster
- •Gemini 3 Flash has a larger context window (1M)
| Gemini 3 Flash | GPT-5.1-Codex | |
|---|---|---|
| Intelligence index | 90.2 | 88.2 |
| Developer | OpenAI | |
| Type | Multimodal | Multimodal |
| Access | API only | API only |
| Context window | 1,048,576 tokens | 400,000 tokens |
| Input price | $0.50 / 1M | $1.25 / 1M |
| Output price | $3.00 / 1M | $10.00 / 1M |
| Speed | 191 tok/s | 188 tok/s |
| Released | December 17, 2025 | November 13, 2025 |
| Parameters | — | — |
| Input modalities | Text, Image, Audio, Video | Text, Image |
| Output modalities | Text | Text |
Shared benchmarks
Gemini 3 Flash
GPT-5.1-Codex
AIME 2025
97
95.7
GPQA Diamond
90.4
86
Humanity’s Last Exam
34.7
23.4
LiveCodeBench
90.8
84.9
MMLU-Pro
89
86