DeepSeek-R1 Benchmark Scores & Performance

Benchmark analysis of DeepSeek-R1 by DeepSeek across 14 tests.

Creator

DeepSeek

Source Type

Open Weight

Reasoning

Reasoning

Context Window

128K

Overall Score

35#73 of 88

Knowledge Benchmarks

MMLU
44
GPQA
43
SuperGPQA
41
OpenBookQA
39

Coding Benchmarks

HumanEval
36

Mathematics Benchmarks

AIME 2023
44
AIME 2024
46
AIME 2025
45
HMMT Feb 2023
40
HMMT Feb 2024
42
HMMT Feb 2025
41
BRUMO 2025
43

Reasoning Benchmarks

SimpleQA
42
MuSR
40

Frequently Asked Questions

How does DeepSeek-R1 perform overall in AI benchmarks?

DeepSeek-R1 ranks #73 out of 88 models with an overall score of 35. It is created by DeepSeek and features a 128K context window.

Is DeepSeek-R1 good for knowledge and understanding?

DeepSeek-R1 ranks #73 out of 88 models in knowledge and understanding benchmarks with an average score of 41.8. There are stronger options in this category.

Is DeepSeek-R1 good for coding and programming?

DeepSeek-R1 ranks #73 out of 88 models in coding and programming benchmarks with an average score of 36. There are stronger options in this category.

Is DeepSeek-R1 good for mathematics?

DeepSeek-R1 ranks #73 out of 88 models in mathematics benchmarks with an average score of 43. There are stronger options in this category.

Is DeepSeek-R1 good for reasoning and logic?

DeepSeek-R1 ranks #73 out of 88 models in reasoning and logic benchmarks with an average score of 41. There are stronger options in this category.

Is DeepSeek-R1 open source?

Yes, DeepSeek-R1 is an open weight model created by DeepSeek, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

What is the context window size of DeepSeek-R1?

DeepSeek-R1 has a context window of 128K tokens, which determines how much text it can process in a single interaction.