AI Hub
← All models

DeepSeek V3.2 Speciale vs Qwen2.5 Coder 32B Instruct

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

  • DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 50.1)
  • DeepSeek V3.2 Speciale is cheaper ($0.29 vs $0.66 per 1M input)
  • DeepSeek V3.2 Speciale has a larger context window (164K)
DeepSeek V3.2 SpecialeQwen2.5 Coder 32B Instruct
Intelligence index89.950.1
DeveloperDeepSeekAlibaba
TypeLLMLLM
AccessOpen weightsOpen weights
Context window163,840 tokens128,000 tokens
Input price$0.29 / 1M$0.66 / 1M
Output price$0.43 / 1M$1.00 / 1M
Speed110 tok/s
ReleasedDecember 1, 2025November 11, 2024
Parameters
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek V3.2 Speciale
Qwen2.5 Coder 32B Instruct
GPQA Diamond
87.1
41.7
Humanity’s Last Exam
26.1
3.8
LiveCodeBench
89.6
31.4
MMLU-Pro
86.3
50.4