token.app โ€บ Compare โ€บ GPT-5 vs DeepSeek V4 Flash 0731

GPT-5 vs DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 leads on 4 of 5 shared benchmarks. DeepSeek V4 Flash 0731 is 31ร— cheaper per token on a blended 3:1 basis. DeepSeek V4 Flash 0731 accepts the larger context window (1.0M).

Head to head
Blended price uses a 3:1 input:output mix
GPT-5DeepSeek V4 Flash 0731
ProviderOpenAIDeepSeek
Input $/1M$1.25$0.090
Output $/1M$10.00$0.180
Blended $/1M$3.44$0.113
Context window400K1.0M
Max output128K384K
ReleasedAug 2025Jul 2026
LicenceProprietaryOpen weights
GPQA Diamond 86.2% 91.0%
FrontierMath T1โ€“3 55.4% 57.5%
FrontierMath T4 22.0% 24.4%
SimpleQA Verified 50.6% 34.7%
OTIS Mock AIME 91.4% 94.4%
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 GPT-5 ifโ€ฆ
  • Higher SimpleQA Verified (50.6% vs 34.7%)
Choose DeepSeek V4 Flash 0731 ifโ€ฆ
  • Costs less per token โ€” $0.113 vs $3.44 blended
  • Higher GPQA Diamond (91.0% vs 86.2%)
  • Higher FrontierMath T1โ€“3 (57.5% vs 55.4%)
  • Higher FrontierMath T4 (24.4% vs 22.0%)
  • Higher OTIS Mock AIME (94.4% vs 91.4%)
  • Larger context window (1.0M)
  • Open weights โ€” self-hostable
  • Newer model (released Jul 2026)
FAQ
Which is better, GPT-5 or DeepSeek V4 Flash 0731?
Across the 5 benchmarks both models have independently-run scores for, GPT-5 leads on 1 and DeepSeek V4 Flash 0731 leads on 4. Benchmarks are one input โ€” price and context window are on this page too.
Is GPT-5 cheaper than DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 is cheaper: $0.113 versus $3.44 per million tokens blended at 3:1 input:output. Input alone: $1.25 vs $0.090. Output alone: $10.00 vs $0.180.
What context windows do GPT-5 and DeepSeek V4 Flash 0731 have?
GPT-5: 400,000 tokens. DeepSeek V4 Flash 0731: 1,048,576 tokens.
Who makes GPT-5 and DeepSeek V4 Flash 0731?
GPT-5 is made by OpenAI. DeepSeek V4 Flash 0731 is made by DeepSeek.
Related comparisons