AI Hub
← All models

DeepSeek-V4-Flash vs Seed-OSS-36B-Instruct

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

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 78.8)
  • DeepSeek-V4-Flash is cheaper ($0.10 vs $0.20 per 1M input)
  • DeepSeek-V4-Flash is faster
DeepSeek-V4-FlashSeed-OSS-36B-Instruct
Intelligence index89.478.8
DeveloperDeepSeekByteDance
TypeLLMLLM
AccessOpen weights
Context window1,048,576 tokens
Input price$0.10 / 1M$0.20 / 1M
Output price$0.20 / 1M$0.60 / 1M
Speed109 tok/s37 tok/s
ReleasedApril 24, 2026August 20, 2025
Parameters284B (13B active)
Input modalitiesText
Output modalitiesText

Shared benchmarks

DeepSeek-V4-Flash
Seed-OSS-36B-Instruct
GPQA Diamond
89.4
72.6
Humanity’s Last Exam
32.1
9.1