AI Hub
← All models

DeepSeek-V4-Flash vs gpt-oss-20b

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

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 73.6)
  • gpt-oss-20b is cheaper ($0.03 vs $0.10 per 1M input)
  • gpt-oss-20b is faster
  • DeepSeek-V4-Flash has a larger context window (1M)
DeepSeek-V4-Flashgpt-oss-20b
Intelligence index89.473.6
DeveloperDeepSeekOpenAI
TypeLLMLLM
AccessOpen weightsOpen weights
Context window1,048,576 tokens131,072 tokens
Input price$0.10 / 1M$0.03 / 1M
Output price$0.20 / 1M$0.14 / 1M
Speed109 tok/s1000 tok/s
ReleasedApril 24, 2026August 5, 2025
Parameters284B (13B active)21B (3.6B active)
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek-V4-Flash
gpt-oss-20b
GPQA Diamond
89.4
71.5
Humanity’s Last Exam
32.1
17.3