AI Hub
← All models

DeepSeek R1 Distill Qwen 1.5B 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 32.6)
  • DeepSeek R1 Distill Qwen 1.5B is cheaper ($0.00 vs $0.29 per 1M input)
DeepSeek R1 Distill Qwen 1.5BDeepSeek V3.2 Speciale
Intelligence index32.689.9
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
Parameters1780000000
Input modalitiesText
Output modalitiesText

Shared benchmarks

DeepSeek R1 Distill Qwen 1.5B
DeepSeek V3.2 Speciale
AIME 2025
22
96.7
GPQA Diamond
33.8
87.1
Humanity’s Last Exam
3.3
26.1
LiveCodeBench
16.9
89.6
MMLU-Pro
26.9
86.3