DeepSeek V4 Pro

deepseek-ai · released 2026-04-24 · mit license

DeepSeek-V4-Pro is a 1.6T-param (49B active) open-weight MoE with 1M context (April 2026), rated the top open model on Artificial Analysis's index (52). NIST/CAISI's independent eval found it trails the frontier and its own vendor numbers.

Key specs

TypeLocal open-weight
Parameters861.61B total · MoE, — active
Architecturedeepseek_v4
Context window1049K tokens
Knowledge cutoff
Modalitiestext
Recommended backends
Minimum viable rig

Benchmark scores

GPQA Diamond90.1%
SWE-bench Verified80.6%
AIME
MMLU-Pro87.5%
BFCL v3 (tool use)
Composite score7.33
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q4_K_M501.2 GB499.7 GB1049K

Strengths & weaknesses

Strengths: Top open-weights model on the Artificial Analysis Intelligence Index at release (52); Top-tier coding: LiveCodeBench 93.5, SWE-bench Verified 80.6 (vendor); 1M-token context, MIT licensed

Weaknesses: NIST/CAISI places real-world capability behind the US frontier; Self-reported scores run higher than independent held-out evals