AI Hub
← All models

Cogito v2.1 vs DeepSeek-V4-Flash

Deep Cogito vs DeepSeek — benchmarks, pricing, and capabilities side by side.

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 75.8)
  • DeepSeek-V4-Flash is cheaper ($0.10 vs $1.30 per 1M input)
  • DeepSeek-V4-Flash is faster
Cogito v2.1DeepSeek-V4-Flash
Intelligence index75.889.4
DeveloperDeep CogitoDeepSeek
TypeLLMLLM
AccessOpen weights
Context window1,048,576 tokens
Input price$1.30 / 1M$0.10 / 1M
Output price$1.30 / 1M$0.20 / 1M
Speed56 tok/s109 tok/s
ReleasedNovember 18, 2025April 24, 2026
Parameters284B (13B active)
Input modalitiesText
Output modalitiesText

Shared benchmarks

Cogito v2.1
DeepSeek-V4-Flash
GPQA Diamond
76.8
89.4
Humanity’s Last Exam
11
32.1