DeepSeek V3.2 (Thinking) Benchmark Scores & Performance

Benchmark analysis of DeepSeek V3.2 (Thinking) by DeepSeek across 14 tests.

Creator

DeepSeek

Source Type

Open Weight

Reasoning

Reasoning

Context Window

128K

Overall Score

69#23 of 88

Knowledge Benchmarks

MMLU
87
GPQA
85
SuperGPQA
83
OpenBookQA
81

Coding Benchmarks

HumanEval
79

Mathematics Benchmarks

AIME 2023
87
AIME 2024
89
AIME 2025
88
HMMT Feb 2023
83
HMMT Feb 2024
85
HMMT Feb 2025
84
BRUMO 2025
86

Reasoning Benchmarks

SimpleQA
83
MuSR
81

Frequently Asked Questions

How does DeepSeek V3.2 (Thinking) perform overall in AI benchmarks?

DeepSeek V3.2 (Thinking) ranks #23 out of 88 models with an overall score of 69. It is created by DeepSeek and features a 128K context window.

Is DeepSeek V3.2 (Thinking) good for knowledge and understanding?

DeepSeek V3.2 (Thinking) ranks #27 out of 88 models in knowledge and understanding benchmarks with an average score of 84. There are stronger options in this category.

Is DeepSeek V3.2 (Thinking) good for coding and programming?

DeepSeek V3.2 (Thinking) ranks #27 out of 88 models in coding and programming benchmarks with an average score of 79. There are stronger options in this category.

Is DeepSeek V3.2 (Thinking) good for mathematics?

DeepSeek V3.2 (Thinking) ranks #27 out of 88 models in mathematics benchmarks with an average score of 86. There are stronger options in this category.

Is DeepSeek V3.2 (Thinking) good for reasoning and logic?

DeepSeek V3.2 (Thinking) ranks #27 out of 88 models in reasoning and logic benchmarks with an average score of 82. There are stronger options in this category.

Is DeepSeek V3.2 (Thinking) open source?

Yes, DeepSeek V3.2 (Thinking) 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 V3.2 (Thinking)?

DeepSeek V3.2 (Thinking) has a context window of 128K tokens, which determines how much text it can process in a single interaction.