AI Hub
← All models

DeepSeek R1 Distill Llama 8B 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 53.3)
  • DeepSeek R1 Distill Llama 8B is cheaper ($0.00 vs $0.29 per 1M input)
DeepSeek R1 Distill Llama 8BDeepSeek V3.2 Speciale
Intelligence index53.389.9
DeveloperDeepSeekDeepSeek
TypeLLMLLM
AccessOpen weightsOpen weights
Context window163,840 tokens
Input price$0.00 / 1M$0.29 / 1M
Output price$0.00 / 1M$0.43 / 1M
Speed
ReleasedJanuary 20, 2025December 1, 2025
Parameters8030000000
Input modalitiesText
Output modalitiesText

Shared benchmarks

DeepSeek R1 Distill Llama 8B
DeepSeek V3.2 Speciale
AIME 2025
41.3
96.7
GPQA Diamond
49
87.1
Humanity’s Last Exam
4.2
26.1
LiveCodeBench
39.6
89.6
MMLU-Pro
54.3
86.3