Gemini 2.0 Flash Thinking vs GPT-5.1-Codex
Google vs OpenAI — benchmarks, pricing, and capabilities side by side.
- •GPT-5.1-Codex has the higher intelligence index (88.2 vs 69.1)
- •Gemini 2.0 Flash Thinking is cheaper ($0.00 vs $1.25 per 1M input)
| Gemini 2.0 Flash Thinking | GPT-5.1-Codex | |
|---|---|---|
| Intelligence index | 69.1 | 88.2 |
| Developer | OpenAI | |
| Type | Multimodal | Multimodal |
| Access | API only | API only |
| Context window | — | 400,000 tokens |
| Input price | $0.00 / 1M | $1.25 / 1M |
| Output price | $0.00 / 1M | $10.00 / 1M |
| Speed | — | 188 tok/s |
| Released | January 21, 2025 | November 13, 2025 |
| Parameters | — | — |
| Input modalities | — | Text, Image |
| Output modalities | — | Text |
Shared benchmarks
Gemini 2.0 Flash Thinking
GPT-5.1-Codex
GPQA Diamond
74.2
86
Humanity’s Last Exam
7.1
23.4
LiveCodeBench
32.1
84.9
MMLU-Pro
79.8
86