DeepSeek V4 Pro — Benchmarks

Benchmark scores for DeepSeek V4 Pro aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #30 of 123 open modelscomposite 59/100 across 9 benchmarks in 4 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
SciCode50.0%#6 / 50#58 / 155
LiveBench Coding70.0#14 / 16#48 / 54

Knowledge

BenchmarkScoreOpen rankAll models
SimpleQA47.0%#3 / 15#28 / 78

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202596.7%#3 / 74#24 / 270
LiveBench Math90.7#2 / 16#23 / 54
ProofBench16.0%#10 / 21#41 / 64

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond90.9%#5 / 83#27 / 291
LiveBench Reasoning82.7#7 / 16#35 / 54
CritPt12.9%#7 / 50#57 / 167

Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.

DeepSeek V4 Pro Benchmarks — Scores & Rankings | llmrun