AI Hub
← All models

DeepSeek-V3 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 58.1)
  • DeepSeek-V3 is cheaper ($0.23 vs $1.50 per 1M input)
  • Gemini 3.5 Flash is faster
  • Gemini 3.5 Flash has a larger context window (1M)
DeepSeek-V3Gemini 3.5 Flash
Intelligence index58.192.2
DeveloperDeepSeekGoogle
TypeLLMMultimodal
AccessOpen weightsAPI only
Context window131,072 tokens1,048,576 tokens
Input price$0.23 / 1M$1.50 / 1M
Output price$0.91 / 1M$9.00 / 1M
Speed100 tok/s221 tok/s
ReleasedDecember 26, 2024May 19, 2026
Parameters671B total / 37B active (MoE)
Input modalitiesTextText, Image, Audio, Video
Output modalitiesTextText

Shared benchmarks

DeepSeek-V3
Gemini 3.5 Flash
GPQA Diamond
59.1
92.2
Humanity’s Last Exam
3.6
41