AI Hub
← All models

DeepSeek V3.2 Speciale vs Qwen2.5-Coder 7B Instruct

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

  • DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 39.6)
  • Qwen2.5-Coder 7B Instruct is cheaper ($0.00 vs $0.29 per 1M input)
DeepSeek V3.2 SpecialeQwen2.5-Coder 7B Instruct
Intelligence index89.939.6
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, 2025September 19, 2024
Parameters7000000000
Input modalitiesText
Output modalitiesText

Shared benchmarks

DeepSeek V3.2 Speciale
Qwen2.5-Coder 7B Instruct
GPQA Diamond
87.1
33.9
Humanity’s Last Exam
26.1
4.8
LiveCodeBench
89.6
18.2
MMLU-Pro
86.3
40.1