DeepSeek R1 0528 — Benchmarks

Benchmark scores for DeepSeek R1 0528 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #13 of 73 open modelscomposite 62.7/100 across 8 benchmarks in 4 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
Aider Polyglot71.4%#2 / 18#19 / 69

Knowledge

BenchmarkScoreOpen rankAll models
SimpleQA27.4%#9 / 11#50 / 65
MMLU-Pro83.4%#11 / 119#46 / 259

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202566.4%#11 / 34#74 / 155
MATH Level 596.6%#1 / 32#9 / 108

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond76.3%#10 / 46#72 / 182
ARC-AGI21.2%#5 / 10#125 / 158
SimpleBench40.8%#9 / 19#59 / 90

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