Artificial intelligence · April 2026

DeepSeek-V4

A 1.6-trillion-parameter open model with a million-token context.

DeepSeek-V4 shipped as open weights in two sizes: V4-Pro with 1.6T total and 49B active parameters, and V4-Flash with 284B and 13B. A 1M-token context became the default, and V4-Pro reached general availability on August 13, 2026.

See it in the living tree Wikipedia Source

Arcs above join it to what it stood on, arcs below to what it led to. The bar places this stretch on the tree's whole timeline.

What it built on 2

DeepSeek sparse attention 2025
DeepSeek-R1 2025

Related measurements

The dashed line marks when it first worked.

Best AI score on GPQA Diamond Latest: 95.8 % correct (2026) Source: Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv); Anthropic: Claude 3 public launch (March 4, 2024)

Training compute of notable AI models Source: Epoch AI, Notable AI Models (CC BY 4.0)