Gemini 3.5 Flash vs Llama 3.2 90B Instruct
Google vs Meta — benchmarks, pricing, and capabilities side by side.
- •Gemini 3.5 Flash has the higher intelligence index (92.2 vs 54)
- •Llama 3.2 90B Instruct is cheaper ($0.35 vs $1.50 per 1M input)
- •Gemini 3.5 Flash is faster
- •Gemini 3.5 Flash has a larger context window (1M)
| Gemini 3.5 Flash | Llama 3.2 90B Instruct | |
|---|---|---|
| Intelligence index | 92.2 | 54 |
| Developer | Meta | |
| Type | Multimodal | Multimodal |
| Access | API only | Open weights |
| Context window | 1,048,576 tokens | 128,000 tokens |
| Input price | $1.50 / 1M | $0.35 / 1M |
| Output price | $9.00 / 1M | $0.40 / 1M |
| Speed | 221 tok/s | 100 tok/s |
| Released | May 19, 2026 | September 25, 2024 |
| Parameters | — | 90000000000 |
| Input modalities | Text, Image, Audio, Video | — |
| Output modalities | Text | — |
Shared benchmarks
Gemini 3.5 Flash
Llama 3.2 90B Instruct
GPQA Diamond
92.2
46.7
Humanity’s Last Exam
41
4.9