DeepSeek Coder V2 Lite Instruct vs Gemini 3.5 Flash
DeepSeek vs Google — benchmarks, pricing, and capabilities side by side.
- •Gemini 3.5 Flash has the higher intelligence index (92.2 vs 30.2)
- •DeepSeek Coder V2 Lite Instruct is cheaper ($0.00 vs $1.50 per 1M input)
| DeepSeek Coder V2 Lite Instruct | Gemini 3.5 Flash | |
|---|---|---|
| Intelligence index | 30.2 | 92.2 |
| Developer | DeepSeek | |
| Type | LLM | Multimodal |
| Access | — | API only |
| Context window | — | 1,048,576 tokens |
| Input price | $0.00 / 1M | $1.50 / 1M |
| Output price | $0.00 / 1M | $9.00 / 1M |
| Speed | — | 221 tok/s |
| Released | June 17, 2024 | May 19, 2026 |
| Parameters | — | — |
| Input modalities | — | Text, Image, Audio, Video |
| Output modalities | — | Text |
Shared benchmarks
DeepSeek Coder V2 Lite Instruct
Gemini 3.5 Flash
GPQA Diamond
31.9
92.2
Humanity’s Last Exam
5.3
41