AI Hub
← All models

DeepSeek V3.2 Speciale vs Qwen3-235B-A22B-Instruct-2507

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

  • DeepSeek V3.2 Speciale has the higher intelligence index (89.9 vs 72.2)
  • Qwen3-235B-A22B-Instruct-2507 is cheaper ($0.15 vs $0.29 per 1M input)
  • DeepSeek V3.2 Speciale has a larger context window (164K)
DeepSeek V3.2 SpecialeQwen3-235B-A22B-Instruct-2507
Intelligence index89.972.2
DeveloperDeepSeekAlibaba
TypeLLMLLM
AccessOpen weightsOpen weights
Context window163,840 tokens131,072 tokens
Input price$0.29 / 1M$0.15 / 1M
Output price$0.43 / 1M$0.80 / 1M
Speed63 tok/s
ReleasedDecember 1, 2025July 22, 2025
Parameters235000000000
Input modalitiesText
Output modalitiesText

Shared benchmarks

DeepSeek V3.2 Speciale
Qwen3-235B-A22B-Instruct-2507
AIME 2025
96.7
70.3
GPQA Diamond
87.1
77.5
Humanity’s Last Exam
26.1
10.6
LiveCodeBench
89.6
52.4
MMLU-Pro
86.3
83