Apertus 70B Instruct vs Gemini 3.5 Flash
Swiss AI Initiative vs Google — benchmarks, pricing, and capabilities side by side.
- •Gemini 3.5 Flash has the higher intelligence index (92.2 vs 27.2)
- •Apertus 70B Instruct is cheaper ($0.80 vs $1.50 per 1M input)
| Apertus 70B Instruct | Gemini 3.5 Flash | |
|---|---|---|
| Intelligence index | 27.2 | 92.2 |
| Developer | Swiss AI Initiative | |
| Type | LLM | Multimodal |
| Access | — | API only |
| Context window | — | 1,048,576 tokens |
| Input price | $0.80 / 1M | $1.50 / 1M |
| Output price | $2.90 / 1M | $9.00 / 1M |
| Speed | — | 221 tok/s |
| Released | September 2, 2025 | May 19, 2026 |
| Parameters | — | — |
| Input modalities | — | Text, Image, Audio, Video |
| Output modalities | — | Text |
Shared benchmarks
Apertus 70B Instruct
Gemini 3.5 Flash
GPQA Diamond
27.2
92.2
Humanity’s Last Exam
5.5
41