AI Hub
← All models

DeepSeek-R1 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 75)
  • 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-R1DeepSeek V3.2 Speciale
Intelligence index7589.9
DeveloperDeepSeekDeepSeek
TypeLLMLLM
AccessOpen weightsOpen weights
Context window128,000 tokens163,840 tokens
Input price$0.55 / 1M$0.29 / 1M
Output price$2.19 / 1M$0.43 / 1M
Speed189 tok/s
ReleasedJanuary 20, 2025December 1, 2025
Parameters671B total / 37B active (MoE)
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek-R1
DeepSeek V3.2 Speciale
AIME 2025
68
96.7
GPQA Diamond
71.5
87.1
Humanity’s Last Exam
9.3
26.1
LiveCodeBench
61.7
89.6
MMLU-Pro
84.4
86.3