token.app โ€บ Compare โ€บ o3 Mini vs DeepSeek V4 Flash 0731

o3 Mini vs DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 leads on 4 of 4 shared benchmarks. DeepSeek V4 Flash 0731 is 17ร— 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
o3 MiniDeepSeek V4 Flash 0731
ProviderOpenAIDeepSeek
Input $/1M$1.10$0.090
Output $/1M$4.40$0.180
Blended $/1M$1.93$0.113
Context window200K1.0M
Max output100K384K
ReleasedJan 2025Jul 2026
LicenceProprietaryOpen weights
GPQA Diamond 77.0% 91.0%
FrontierMath T1โ€“3 18.6% 57.5%
FrontierMath T4 0.0% 24.4%
OTIS Mock AIME 76.9% 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 o3 Mini ifโ€ฆ
  • No clear advantage on the data we hold.
Choose DeepSeek V4 Flash 0731 ifโ€ฆ
  • Costs less per token โ€” $0.113 vs $1.93 blended
  • Higher GPQA Diamond (91.0% vs 77.0%)
  • Higher FrontierMath T1โ€“3 (57.5% vs 18.6%)
  • Higher FrontierMath T4 (24.4% vs 0.0%)
  • Higher OTIS Mock AIME (94.4% vs 76.9%)
  • Larger context window (1.0M)
  • Open weights โ€” self-hostable
  • Newer model (released Jul 2026)
FAQ
Which is better, o3 Mini or DeepSeek V4 Flash 0731?
Across the 4 benchmarks both models have independently-run scores for, o3 Mini leads on 0 and DeepSeek V4 Flash 0731 leads on 4. Benchmarks are one input โ€” price and context window are on this page too.
Is o3 Mini cheaper than DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 is cheaper: $0.113 versus $1.93 per million tokens blended at 3:1 input:output. Input alone: $1.10 vs $0.090. Output alone: $4.40 vs $0.180.
What context windows do o3 Mini and DeepSeek V4 Flash 0731 have?
o3 Mini: 200,000 tokens. DeepSeek V4 Flash 0731: 1,048,576 tokens.
Who makes o3 Mini and DeepSeek V4 Flash 0731?
o3 Mini is made by OpenAI. DeepSeek V4 Flash 0731 is made by DeepSeek.
Related comparisons