AI Hub
← All models

DeepSeek-V4-Flash vs Qwen3 235B A22B 2507

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

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 84.2)
  • DeepSeek-V4-Flash is cheaper ($0.10 vs $0.40 per 1M input)
  • DeepSeek-V4-Flash is faster
DeepSeek-V4-FlashQwen3 235B A22B 2507
Intelligence index89.484.2
DeveloperDeepSeekAlibaba
TypeLLMLLM
AccessOpen weights
Context window1,048,576 tokens
Input price$0.10 / 1M$0.40 / 1M
Output price$0.20 / 1M$2.20 / 1M
Speed109 tok/s59 tok/s
ReleasedApril 24, 2026July 25, 2025
Parameters284B (13B active)
Input modalitiesText
Output modalitiesText

Shared benchmarks

DeepSeek-V4-Flash
Qwen3 235B A22B 2507
GPQA Diamond
89.4
79
Humanity’s Last Exam
32.1
15