AI Hub
← All models

DeepSeek V3.2 Speciale vs Granite 4.0 Micro

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

  • DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 25.6)
  • Granite 4.0 Micro is cheaper ($0.02 vs $0.29 per 1M input)
  • DeepSeek V3.2 Speciale has a larger context window (164K)
DeepSeek V3.2 SpecialeGranite 4.0 Micro
Intelligence index89.925.6
DeveloperDeepSeekIBM
TypeLLMLLM
AccessOpen weightsOpen weights
Context window163,840 tokens131,000 tokens
Input price$0.29 / 1M$0.02 / 1M
Output price$0.43 / 1M$0.11 / 1M
Speed
ReleasedDecember 1, 2025October 20, 2025
Parameters
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek V3.2 Speciale
Granite 4.0 Micro
AIME 2025
96.7
6
GPQA Diamond
87.1
33.6
Humanity’s Last Exam
26.1
5.1
LiveCodeBench
89.6
18
MMLU-Pro
86.3
44.7