AI Hub
← All models

DeepSeek R1 0528 Qwen3 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 66.2)
  • DeepSeek R1 0528 Qwen3 8B is cheaper ($0.00 vs $0.29 per 1M input)
DeepSeek R1 0528 Qwen3 8BDeepSeek V3.2 Speciale
Intelligence index66.289.9
DeveloperDeepSeekDeepSeek
TypeLLMLLM
AccessOpen weights
Context window163,840 tokens
Input price$0.00 / 1M$0.29 / 1M
Output price$0.00 / 1M$0.43 / 1M
Speed
ReleasedMay 29, 2025December 1, 2025
Parameters
Input modalitiesText
Output modalitiesText

Shared benchmarks

DeepSeek R1 0528 Qwen3 8B
DeepSeek V3.2 Speciale
AIME 2025
63.7
96.7
GPQA Diamond
61.2
87.1
Humanity’s Last Exam
5.6
26.1
LiveCodeBench
51.3
89.6
MMLU-Pro
73.9
86.3