DeepSeek V4 Pro

DeepSeek · deepseek/deepseek-v4-pro

ProviderDeepSeek
Familydeepseek-thinking
Typellm-reasoning
Statusactive
Released2026-08-12
Updated2026-08-22
Open weightsyes

Capabilities

Chain Of Thought · tier-2 Function Calling · tier-2

Reported benchmark scores

This card reports no benchmark scores yet.

BenchmarkCatalogue standingScore

Data

This card as JSON · See it in the graph · Edit on GitHub