Gemini 3 Flash Preview vs DeepSeek V4 Flash 0731

Gemini 3 Flash Preview vs DeepSeek V4 Flash 0731: which AI model is cheaper, has the larger context window and more capabilities? Side-by-side comparison updated daily.

Quick verdict

  • DeepSeek V4 Flash 0731 is 12× cheaper than Gemini 3 Flash Preview for the same mix of input and output tokens.
  • Both have the same context window.
  • DeepSeek V4 Flash 0731 is the more recent release (Jul 31, 2026).
  • Only DeepSeek V4 Flash 0731 has openly published weights you can run yourself.
  • Only Gemini 3 Flash Preview accepts images as input.
  • DeepSeek V4 Flash 0731 scores higher on independent tests (overall index 154.5 vs 151.8).
  • DeepSeek V4 Flash 0731 is both cheaper and better rated: for most uses it is the better choice.
Gemini 3 Flash PreviewDeepSeek V4 Flash 0731
CompanyGoogle DeepMindDeepSeek
ReleasedDec 17, 2025Jul 31, 2026 ●
Overall index151.8154.5 ●
SWE-bench Verified75.4%—
GPQA Diamond89.4%91.0% ●
AIME math95.6% ●94.4%
FrontierMath51.2%57.5% ●
SimpleQA Verified66.8% ●33.6%
Input (per 1M tokens)$0.50$0.018 ●
Output (per 1M tokens)$3$0.32 ●
Cost for 1M input + 1M output tokens$3.50$0.338 ●
Providers630 ●
Context1M1M
Max output64K944K ●
InputsText, Image, Files, Audio, Video ●Text
OutputsTextText
Reasoning✓✓
Tool use✓✓
Structured output✓✓
Open weights—✓

Add a model →

Popular comparisons