AI Hub
← All models

DeepSeek-R1-0528 vs DeepSeek V3.2 Speciale

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

  • DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 63.3)
  • DeepSeek V3.2 Speciale is cheaper ($0.29 vs $0.55 per 1M input)
  • DeepSeek V3.2 Speciale has a larger context window (164K)
DeepSeek-R1-0528DeepSeek V3.2 Speciale
Intelligence index63.389.9
DeveloperDeepSeekDeepSeek
TypeLLMLLM
AccessOpen weightsOpen weights
Context window131,072 tokens163,840 tokens
Input price$0.55 / 1M$0.29 / 1M
Output price$2.19 / 1M$0.43 / 1M
Speed45 tok/s
ReleasedMay 28, 2025December 1, 2025
Parameters671000000000
Input modalitiesText
Output modalitiesText

Shared benchmarks

DeepSeek-R1-0528
DeepSeek V3.2 Speciale
AIME 2025
87.5
96.7
GPQA Diamond
81
87.1
Humanity’s Last Exam
17.7
26.1
LiveCodeBench
73.3
89.6
MMLU-Pro
85
86.3