AI Hub
← All models

DBRX Instruct vs DeepSeek-V4-Flash

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

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 27.5)
  • DBRX Instruct is cheaper ($0.00 vs $0.10 per 1M input)
DBRX InstructDeepSeek-V4-Flash
Intelligence index27.589.4
DeveloperDatabricksDeepSeek
TypeLLMLLM
AccessOpen weights
Context window1,048,576 tokens
Input price$0.00 / 1M$0.10 / 1M
Output price$0.00 / 1M$0.20 / 1M
Speed109 tok/s
ReleasedMarch 27, 2024April 24, 2026
Parameters284B (13B active)
Input modalitiesText
Output modalitiesText

Shared benchmarks

DBRX Instruct
DeepSeek-V4-Flash
GPQA Diamond
33.1
89.4
Humanity’s Last Exam
6.6
32.1