AI Hub
← All models

DeepSeek V3.2 Speciale vs DeepSeek-V4-Flash

DeepSeek vs DeepSeek — benchmarks, pricing, and capabilities side by side.

  • DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 89.4)
  • DeepSeek-V4-Flash is cheaper ($0.10 vs $0.29 per 1M input)
  • DeepSeek-V4-Flash has a larger context window (1M)
DeepSeek V3.2 SpecialeDeepSeek-V4-Flash
Intelligence index89.989.4
DeveloperDeepSeekDeepSeek
TypeLLMLLM
AccessOpen weightsOpen weights
Context window163,840 tokens1,048,576 tokens
Input price$0.29 / 1M$0.10 / 1M
Output price$0.43 / 1M$0.20 / 1M
Speed109 tok/s
ReleasedDecember 1, 2025April 24, 2026
Parameters284B (13B active)
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek V3.2 Speciale
DeepSeek-V4-Flash
GPQA Diamond
87.1
89.4
Humanity’s Last Exam
26.1
32.1