AI Hub
← All models

DeepSeek-V4-Flash vs Qwen3.6 Max

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

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 88.8)
  • DeepSeek-V4-Flash is cheaper ($0.10 vs $1.04 per 1M input)
  • DeepSeek-V4-Flash is faster
  • DeepSeek-V4-Flash has a larger context window (1M)
DeepSeek-V4-FlashQwen3.6 Max
Intelligence index89.488.8
DeveloperDeepSeekAlibaba
TypeLLMLLM
AccessOpen weightsAPI only
Context window1,048,576 tokens262,144 tokens
Input price$0.10 / 1M$1.04 / 1M
Output price$0.20 / 1M$6.24 / 1M
Speed109 tok/s36 tok/s
ReleasedApril 24, 2026April 27, 2026
Parameters284B (13B active)
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek-V4-Flash
Qwen3.6 Max
GPQA Diamond
89.4
88.8
Humanity’s Last Exam
32.1
28.9