AI Hub
← All models

DeepSeek V3.2 Speciale vs MiniMax M2.1

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

  • DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 83.6)
  • DeepSeek V3.2 Speciale is cheaper ($0.29 vs $0.29 per 1M input)
  • MiniMax M2.1 has a larger context window (205K)
DeepSeek V3.2 SpecialeMiniMax M2.1
Intelligence index89.983.6
DeveloperDeepSeekMiniMax
TypeLLMLLM
AccessOpen weightsOpen weights
Context window163,840 tokens204,800 tokens
Input price$0.29 / 1M$0.29 / 1M
Output price$0.43 / 1M$0.95 / 1M
Speed92 tok/s
ReleasedDecember 1, 2025December 23, 2025
Parameters
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek V3.2 Speciale
MiniMax M2.1
AIME 2025
96.7
82.7
GPQA Diamond
87.1
83
Humanity’s Last Exam
26.1
22.2
LiveCodeBench
89.6
81
MMLU-Pro
86.3
87.5