AI Hub
← All models

DeepSeek V3.2 Speciale vs Granite 4.1 8B

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

  • DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 43.3)
  • Granite 4.1 8B is cheaper ($0.05 vs $0.29 per 1M input)
  • DeepSeek V3.2 Speciale has a larger context window (164K)
DeepSeek V3.2 SpecialeGranite 4.1 8B
Intelligence index89.943.3
DeveloperDeepSeekIBM
TypeLLMLLM
AccessOpen weightsOpen weights
Context window163,840 tokens131,072 tokens
Input price$0.29 / 1M$0.05 / 1M
Output price$0.43 / 1M$0.10 / 1M
Speed133 tok/s
ReleasedDecember 1, 2025April 30, 2026
Parameters
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek V3.2 Speciale
Granite 4.1 8B
GPQA Diamond
87.1
43.3
Humanity’s Last Exam
26.1
3.8