DE
DeepSeek
Language model · China ·May 2025

DeepSeek-R1-0528

Language Proprietary
22
Benchmarks

About DeepSeek-R1-0528

DeepSeek-R1-0528 is an AI model developed by DeepSeek, in the language category, released in 2025, made available as a proprietary (API-only) model. Updated R1 model release (R1-0528)..

On this page you'll find DeepSeek-R1-0528's full specifications, including 22 benchmark results. Review provider pricing and benchmark scores below, or compare DeepSeek-R1-0528 head-to-head with other language models.

Links

Community

Would you run DeepSeek-R1-0528 again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

DeepSeek-R1-0528 benchmark scores
Benchmark Category Score Variant
Terminal-Bench 2.0 agentic 17.5%
LiveCodeBench code 77% 2407-2501
LiveCodeBench v5 code 75.2% reasoning
LiveCodeBench v6 code 70.3% reasoning
SWE-bench Verified code 41.4%
SciCode code 40.3%
IFEval general 87.8%
IFEval general 80.8% reasoning
MMLU general 89.1%
MMLU-Pro general 85% reasoning
MMLU-Pro general 84.9%
MMLU-Redux general 93.4% reasoning
MultiChallenge general 58.2%
AIME 2024 math 89.3%
AIME 2025 math 87.5% reasoning
HMMT February 2025 math 79.4% reasoning
MATH-500 math 99.3%
GPQA Diamond reasoning 81.3%
GPQA Diamond reasoning 81% reasoning
Humanity's Last Exam reasoning 14.9%
SimpleQA safety 27.8%
BFCL v3 tool-use 64.7% reasoning

More models like DeepSeek-R1-0528

Frequently asked questions

What is DeepSeek-R1-0528?

Updated R1 model release (R1-0528). It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created DeepSeek-R1-0528?

DeepSeek-R1-0528 was developed by DeepSeek and released in 2025.

Is DeepSeek-R1-0528 open source or proprietary?

DeepSeek-R1-0528 is a proprietary model. It is accessed through an API rather than by downloading the weights.

How much does DeepSeek-R1-0528 cost?

Pricing for DeepSeek-R1-0528 depends on the provider. See the providers table on this page for the latest API rates.

How does DeepSeek-R1-0528 perform on benchmarks?

DeepSeek-R1-0528 is benchmarked across 22 evaluations on GenAIList, including Terminal-Bench 2.0 (17.5%). See the full benchmark table below and compare it with other models.

No videos yet. Know a good one? Add it below.

Know a great video about DeepSeek-R1-0528?