Gemini 3.5 Flash vs Mixtral 8x22B Instruct
Google vs Mistral AI — benchmarks, pricing, and capabilities side by side.
- •Gemini 3.5 Flash has the higher intelligence index (92.2 vs 39.1)
- •Gemini 3.5 Flash is cheaper ($1.50 vs $2.00 per 1M input)
- •Gemini 3.5 Flash has a larger context window (1M)
| Gemini 3.5 Flash | Mixtral 8x22B Instruct | |
|---|---|---|
| Intelligence index | 92.2 | 39.1 |
| Developer | Mistral AI | |
| Type | Multimodal | LLM |
| Access | API only | Open weights |
| Context window | 1,048,576 tokens | 65,536 tokens |
| Input price | $1.50 / 1M | $2.00 / 1M |
| Output price | $9.00 / 1M | $6.00 / 1M |
| Speed | 221 tok/s | — |
| Released | May 19, 2026 | April 17, 2024 |
| Parameters | — | — |
| Input modalities | Text, Image, Audio, Video | Text |
| Output modalities | Text | Text |
Shared benchmarks
Gemini 3.5 Flash
Mixtral 8x22B Instruct
GPQA Diamond
92.2
33.2
Humanity’s Last Exam
41
4.1