AI Hub
← All models

DeepSeek-V4-Flash vs INTELLECT-3

DeepSeek vs Prime Intellect — benchmarks, pricing, and capabilities side by side.

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 81)
  • DeepSeek-V4-Flash is cheaper ($0.10 vs $0.20 per 1M input)
  • DeepSeek-V4-Flash has a larger context window (1M)
DeepSeek-V4-FlashINTELLECT-3
Intelligence index89.481
DeveloperDeepSeekPrime Intellect
TypeLLMLLM
AccessOpen weightsOpen weights
Context window1,048,576 tokens131,072 tokens
Input price$0.10 / 1M$0.20 / 1M
Output price$0.20 / 1M$1.10 / 1M
Speed109 tok/s
ReleasedApril 24, 2026November 27, 2025
Parameters284B (13B active)
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek-V4-Flash
INTELLECT-3
GPQA Diamond
89.4
76.1
Humanity’s Last Exam
32.1
12.1