Gemini 3.5 Flash vs Granite 4.1 8B
Google vs IBM — benchmarks, pricing, and capabilities side by side.
- •Gemini 3.5 Flash has the higher intelligence index (92.2 vs 43.3)
- •Granite 4.1 8B is cheaper ($0.05 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 | Granite 4.1 8B | |
|---|---|---|
| Intelligence index | 92.2 | 43.3 |
| Developer | IBM | |
| Type | Multimodal | LLM |
| Access | API only | Open weights |
| Context window | 1,048,576 tokens | 131,072 tokens |
| Input price | $1.50 / 1M | $0.05 / 1M |
| Output price | $9.00 / 1M | $0.10 / 1M |
| Speed | 221 tok/s | 133 tok/s |
| Released | May 19, 2026 | April 30, 2026 |
| Parameters | — | — |
| Input modalities | Text, Image, Audio, Video | Text |
| Output modalities | Text | Text |
Shared benchmarks
Gemini 3.5 Flash
Granite 4.1 8B
GPQA Diamond
92.2
43.3
Humanity’s Last Exam
41
3.8