AI Hub
← All models

DeepSeek V3.2 Speciale vs Olmo 3 32B Think

DeepSeek vs Allen Institute for AI — benchmarks, pricing, and capabilities side by side.

  • DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 69.5)
  • Olmo 3 32B Think is cheaper ($0.15 vs $0.29 per 1M input)
  • DeepSeek V3.2 Speciale has a larger context window (164K)
DeepSeek V3.2 SpecialeOlmo 3 32B Think
Intelligence index89.969.5
DeveloperDeepSeekAllen Institute for AI
TypeLLMLLM
AccessOpen weightsOpen weights
Context window163,840 tokens65,536 tokens
Input price$0.29 / 1M$0.15 / 1M
Output price$0.43 / 1M$0.50 / 1M
Speed
ReleasedDecember 1, 2025November 21, 2025
Parameters
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek V3.2 Speciale
Olmo 3 32B Think
AIME 2025
96.7
73.7
GPQA Diamond
87.1
61
Humanity’s Last Exam
26.1
5.9
LiveCodeBench
89.6
67.2
MMLU-Pro
86.3
75.9