AI Hub
← All models

DeepSeek V3.2 Speciale vs Qwen2 72B Instruct

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

  • DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 59.9)
  • Qwen2 72B Instruct is cheaper ($0.00 vs $0.29 per 1M input)
DeepSeek V3.2 SpecialeQwen2 72B Instruct
Intelligence index89.959.9
DeveloperDeepSeekAlibaba
TypeLLMLLM
AccessOpen weightsOpen weights
Context window163,840 tokens
Input price$0.29 / 1M$0.00 / 1M
Output price$0.43 / 1M$0.00 / 1M
Speed
ReleasedDecember 1, 2025July 23, 2024
Parameters72000000000
Input modalitiesText
Output modalitiesText

Shared benchmarks

DeepSeek V3.2 Speciale
Qwen2 72B Instruct
GPQA Diamond
87.1
42.4
Humanity’s Last Exam
26.1
3.7
LiveCodeBench
89.6
15.9
MMLU-Pro
86.3
64.4