token.app โ€บ Compare โ€บ Mistral Medium 3 vs DeepSeek V4 Flash 0731

Mistral Medium 3 vs DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 leads on 2 of 2 shared benchmarks. DeepSeek V4 Flash 0731 is 7.1ร— 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
Mistral Medium 3DeepSeek V4 Flash 0731
ProviderMistral AIDeepSeek
Input $/1M$0.400$0.090
Output $/1M$2.00$0.180
Blended $/1M$0.800$0.113
Context window131K1.0M
Max outputโ€”384K
ReleasedMay 2025Jul 2026
LicenceProprietaryOpen weights
GPQA Diamond 59.5% 91.0%
OTIS Mock AIME 32.2% 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 Mistral Medium 3 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 $0.800 blended
  • Higher GPQA Diamond (91.0% vs 59.5%)
  • Higher OTIS Mock AIME (94.4% vs 32.2%)
  • Larger context window (1.0M)
  • Open weights โ€” self-hostable
  • Newer model (released Jul 2026)
FAQ
Which is better, Mistral Medium 3 or DeepSeek V4 Flash 0731?
Across the 2 benchmarks both models have independently-run scores for, Mistral Medium 3 leads on 0 and DeepSeek V4 Flash 0731 leads on 2. Benchmarks are one input โ€” price and context window are on this page too.
Is Mistral Medium 3 cheaper than DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 is cheaper: $0.113 versus $0.800 per million tokens blended at 3:1 input:output. Input alone: $0.400 vs $0.090. Output alone: $2.00 vs $0.180.
What context windows do Mistral Medium 3 and DeepSeek V4 Flash 0731 have?
Mistral Medium 3: 131,072 tokens. DeepSeek V4 Flash 0731: 1,048,576 tokens.
Who makes Mistral Medium 3 and DeepSeek V4 Flash 0731?
Mistral Medium 3 is made by Mistral AI. DeepSeek V4 Flash 0731 is made by DeepSeek.
Related comparisons