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.

Coding

BenchmarkScoreRank
Aider Polyglot71.4%#1 / 12

Knowledge

BenchmarkScoreRank
SimpleQA27.4%#4 / 4

Math

BenchmarkScoreRank
AIME 2024/202566.4%#5 / 22
MATH Level 596.6%#1 / 23

Reasoning

BenchmarkScoreRank
GPQA Diamond76.3%#5 / 28
ARC-AGI21.2%#3 / 7
SimpleBench40.8%#4 / 10

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