AI Hub
← All models

DeepSeek-V4-Flash vs GPT-5.2

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

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 86.2)
  • DeepSeek-V4-Flash is cheaper ($0.10 vs $1.75 per 1M input)
  • DeepSeek-V4-Flash is faster
  • DeepSeek-V4-Flash has a larger context window (1M)
DeepSeek-V4-FlashGPT-5.2
Intelligence index89.486.2
DeveloperDeepSeekOpenAI
TypeLLMLLM
AccessOpen weightsAPI only
Context window1,048,576 tokens400,000 tokens
Input price$0.10 / 1M$1.75 / 1M
Output price$0.20 / 1M$14.00 / 1M
Speed109 tok/s73 tok/s
ReleasedApril 24, 2026December 11, 2025
Parameters284B (13B active)
Input modalitiesTextText, Image
Output modalitiesTextText

Shared benchmarks

DeepSeek-V4-Flash
GPT-5.2
GPQA Diamond
89.4
92.4
Humanity’s Last Exam
32.1
35.4