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: #3 of 73 open modelscomposite 74.3/100 across 7 benchmarks in 4 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
LiveBench Coding70.0#6 / 8#32 / 37

Knowledge

BenchmarkScoreOpen rankAll models
SimpleQA57.0%#1 / 11#12 / 65

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202596.7%#1 / 34#11 / 155
LiveBench Math90.7#1 / 8#15 / 37

Reasoning

BenchmarkScoreOpen rankAll models
SimpleBench61.2%#1 / 19#22 / 90
GPQA Diamond89.6%#2 / 46#23 / 182
LiveBench Reasoning82.7#2 / 8#23 / 37

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