token.app โ€บ Compare โ€บ DeepSeek V4 Flash 0731 vs Gemini 3.7 Flash

DeepSeek V4 Flash 0731 vs Gemini 3.7 Flash

Gemini 3.7 Flash leads on 4 of 4 shared benchmarks. DeepSeek V4 Flash 0731 is 2.3ร— cheaper per token on a blended 3:1 basis.

Head to head
Blended price uses a 3:1 input:output mix
DeepSeek V4 Flash 0731Gemini 3.7 Flash
ProviderDeepSeekGoogle
Input $/1M$0.440$0.750
Output $/1M$1.32$3.75
Blended $/1M$0.660$1.50
Context window1.0M1.0M
Max output131K66K
ReleasedJul 2026Aug 2026
LicenceOpen weightsProprietary
GPQA Diamond 91.0% 94.8%
FrontierMath T1โ€“3 57.5% 71.6%
FrontierMath T4 24.4% 36.6%
OTIS Mock AIME 94.4% 97.2%
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose DeepSeek V4 Flash 0731 ifโ€ฆ
  • Costs less per token โ€” $0.660 vs $1.50 blended
  • Open weights โ€” self-hostable
Choose Gemini 3.7 Flash ifโ€ฆ
  • Higher GPQA Diamond (94.8% vs 91.0%)
  • Higher FrontierMath T1โ€“3 (71.6% vs 57.5%)
  • Higher FrontierMath T4 (36.6% vs 24.4%)
  • Higher OTIS Mock AIME (97.2% vs 94.4%)
  • Newer model (released Aug 2026)
FAQ
Which is better, DeepSeek V4 Flash 0731 or Gemini 3.7 Flash?
Across the 4 benchmarks both models have independently-run scores for, DeepSeek V4 Flash 0731 leads on 0 and Gemini 3.7 Flash leads on 4. Benchmarks are one input โ€” price and context window are on this page too.
Is DeepSeek V4 Flash 0731 cheaper than Gemini 3.7 Flash?
DeepSeek V4 Flash 0731 is cheaper: $0.660 versus $1.50 per million tokens blended at 3:1 input:output. Input alone: $0.440 vs $0.750. Output alone: $1.32 vs $3.75.
What context windows do DeepSeek V4 Flash 0731 and Gemini 3.7 Flash have?
DeepSeek V4 Flash 0731: 1,048,576 tokens. Gemini 3.7 Flash: 1,048,576 tokens.
Who makes DeepSeek V4 Flash 0731 and Gemini 3.7 Flash?
DeepSeek V4 Flash 0731 is made by DeepSeek. Gemini 3.7 Flash is made by Google.
Related comparisons